Frank K. Soong

发表

Speaker characterization using spectral subband energy ratio based on Harmonic plus Noise Model

Yanhua Long, Zhi-Jie Yan, Frank K. Soong, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discriminative training for improving letter-to-sound conversion performance

Frank K. Soong, Yining Chen, Peng Liu, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

A symbol graph based handwritten math expression recognition

Frank K. Soong, Yu Shi, 2008, 2008 19th International Conference on Pattern Recognition.

Improving mispronunciation detection using machine learning

Frank K. Soong, Chao Huang, Yuqiang Chen, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Minimum Error Rate Pattern Recognition Approach to Speech Recognition

Biing-Hwang Juang, Chin-Hui Lee, Frank K. Soong, 1994, Int. J. Pattern Recognit. Artif. Intell..

Generalized posterior probability for minimizing verification errors at subword, word and sentence levels

Satoshi Nakamura, Frank K. Soong, Wai Kit Lo, 2004, 2004 International Symposium on Chinese Spoken Language Processing.

A Quadratic Optimization Approach to Discriminative Training of CDHMMs

Frank K. Soong, Peng Liu, 2009, IEEE Signal Processing Letters.

Auto-segmentation based VAD for robust ASR

Frank K. Soong, Yu Shi, Jian-Lai Zhou, 2006, INTERSPEECH.

High performance connected digit recognition using hidden Markov models

Frank K. Soong, Lawrence R. Rabiner, Jay G. Wilpon, 1989, IEEE Trans. Acoust. Speech Signal Process..

A Refined Query-by-Example Approach to Spoken-Term-Detection on ESL learners’ Speech

Lei Xie, Frank K. Soong, Wenping Hu, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Tip tap tones: mobile microtraining of mandarin sounds

Frank K. Soong, Darren Edge, Yao Qian, 2012, Mobile HCI.

Model-based speech separation with single-microphone input

Frank K. Soong, Pak-Chung Ching, Siu Wa Lee, 2007, INTERSPEECH.

Voice conversion with SI-DNN and KL divergence based mapping without parallel training data

Frank K. Soong, Haifeng Li, Feng-Long Xie, 2019, Speech Commun..

Cross-validation based decision tree clustering for HMM-based TTS

Zhi-Jie Yan, Frank K. Soong, Yu Zhang, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Full HMM Training for Minimizing Generation Error in Synthesis

Frank K. Soong, Ren-Hua Wang, Yi-Jian Wu, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Improved Time-Frequency Trajectory Excitation Vocoder for DNN-Based Speech Synthesis

Frank K. Soong, Hong-Goo Kang, Eunwoo Song, 2016, INTERSPEECH.

Discriminative training of high performance speech recognizer using N best candidates

Frank K. Soong, Jung-Kuei Chen, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Improvements in Speaker Characterization Using Spectral Subband Energy Based on Harmonic plus Noise Model

Yanhua Long, Zhi-Jie Yan, Frank K. Soong, 2011, INTERSPEECH.

Duration refinement by jointly optimizing state and longer unit likelihood

Zhizheng Wu, Frank K. Soong, Boyang Gao, 2008, INTERSPEECH.

Hands-free human-machine dialogue - corpora, technology and evaluation

Frank K. Soong, Eric A. Woudenberg, 2000, INTERSPEECH.

Robust F0 modeling for Mandarin speech recognition in noise

Frank K. Soong, Congfu Xu, Yao Qian, 2007, INTERSPEECH.

Improving Automatic Evaluation of Mandarin Pronunciation with Speaker Adaptive Training (SAT) and MLLR Speaker Adaption

Frank K. Soong, Feng Zhang, Chao Huang, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

Non-uniform Kernel Allocation Based Parsimonious HMM

Frank K. Soong, Peng Liu, Jian-Lai Zhou, 2006, ISCSLP.

Constrained Multichannel Speech Dereverberation

Frank K. Soong, Meng Yu, 2012, INTERSPEECH.

Context-dependent boundary modeling for automatic segmentation of TTS units

Frank K. Soong, Lijuan Wang, 2006 .

Computer-Assisted Audiovisual Language Learning

Gang Chen, Frank K. Soong, Lijuan Wang, 2012, Computer.

An HMM-based bilingual (Mandarin-English) TTS

Frank K. Soong, Hui Liang, Yao Qian, 2007, SSW.

Optimal clustering and non-uniform allocation of Gaussian kernels in scalar dimension for HMM compression [speech recognition applications]

Frank K. Soong, Ren-Hua Wang, Tor André Myrvoll, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

A maximum a Posterior-based reconstruction approach to speech bandwidth expansion in noise

Frank K. Soong, Hong-Goo Kang, Hyunson Seo, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Quantizing mixture-weights in a tied-mixture HMM

Frank K. Soong, Raziel Haimi-Cohen, Sunil K. Gupta, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition

Frank K. Soong, Eng-Fong Huang, F. Soong, 1990, HLT.

Generating natural F0 trajectory with additive trees

Frank K. Soong, Hui Liang, Yao Qian, 2008, INTERSPEECH.

A real-time Japanese broadcast news closed-captioning system

Feng Liu, Kazuo Onoe, Akio Ando, 2001, INTERSPEECH.

Modeling F0 trajectories in hierarchically structured deep neural networks

Frank K. Soong, Li-Rong Dai, Zhen-Hua Ling, 2016, Speech Commun..

A new language independent, photo-realistic talking head driven by voice only

Frank K. Soong, Lijuan Wang, Gang Li, 2013, INTERSPEECH.

State mapping for cross-language speaker adaptation in TTS

Frank K. Soong, Yining Chen, Yang Jiao, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

A New GAN-based End-to-End TTS Training Algorithm

Lei Xie, Frank K. Soong, Lei He, 2019, INTERSPEECH.

Sequence error (SE) minimization training of neural network for voice conversion

Haifeng Li, Frank K. Soong, Yao Qian, 2014, INTERSPEECH.

Phonetic transcription verification with generalized posterior probability

Zhigang Cao, Frank K. Soong, Yong Zhao, 2005, INTERSPEECH.

Forward-Backward Decoding for Regularizing End-to-End TTS pdf

Frank K. Soong, Lei He, Zhengqi Wen, 2019, INTERSPEECH.

Optimal quantization of LSP parameters (speech coding)

Frank K. Soong, B.-H. Juang, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Word Graph Based Feature Enhancement for Noisy Speech Recognition

Zhi-Jie Yan, Frank K. Soong, Ren-Hua Wang, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

A fast algorithm for large vocabulary keyword spotting application

Frank K. Soong, Eng-Fong Huang, Hsiao-Chuan Wang, 1994, IEEE Trans. Speech Audio Process..

An Iterative Trajectory Regeneration Algorithm for Separating Mixed Speech Sources

Frank K. Soong, Pak-Chung Ching, Siu Wa Lee, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis

Frank K. Soong, Wenping Hu, Yao Qian, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improved modeling for F0 generation and V/U decision in HMM-based TTS

Yonghong Yan, Frank K. Soong, Qingqing Zhang, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A deep bidirectional LSTM approach for video-realistic talking head

Frank K. Soong, Lei Xie, Lijuan Wang, 2016, Multimedia Tools and Applications.

Minimum Error Discriminative Training for Radical-Based Online Chinese Handwriting Recognition

Frank K. Soong, Yu Zhang, Peng Liu, 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

Modeling DCT parameterized F0 trajectory at intonation phrase level with DNN or decision tree

Frank K. Soong, Li-Rong Dai, Zhen-Hua Ling, 2014, INTERSPEECH.

A Constrained Line Search Optimization for Discriminative Training in Speech Recognition

Frank K. Soong, Peng Liu, Ren-Hua Wang, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Optimal quantization of LSP parameters

Biing-Hwang Juang, Frank K. Soong, B. Juang, 1993, IEEE Trans. Speech Audio Process..

A Segmentation Posterior Based Endpointing Algorithm

Frank K. Soong, Yu Shi, Yanlu Xie, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Radical based fine trajectory HMMs of online handwritten characters

Frank K. Soong, Peng Liu, Lei Ma, 2008, 2008 19th International Conference on Pattern Recognition.

Tip tap tones: mobile microtraining of mandarin sounds

Frank K. Soong, Darren Edge, Yao Qian, 2012, Mobile HCI.

Fast spectral estimation of speech signal in analytic form

Frank K. Soong, Allen M. Peterson, 1980, ICASSP.

Generalized mixture of HMMs for continuous speech recognition

Biing-Hwang Juang, Frank K. Soong, Filipp Korkmazskiy, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The use of tree-trellis search for large-vocabulary Mandarin polysyllabic word speech recognition

Frank K. Soong, Hsiao-Chuan Wang, Eng-Fong Huang, 1994, Comput. Speech Lang..

Automatic prosody prediction and detection with Conditional Random Field (CRF) models

Zhizheng Wu, Frank K. Soong, Xuezhe Ma, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

Observations on linear estimation

Frank K. Soong, Leland B. Jackson, 1978, ICASSP.

連続音声認識候補受理/リジェクションのためのワードスポッティング仮説検証手法(第5回音声言語シンポジウム : システム・信頼度)

Frank K. Soong, Wai Kit Lo, 中村哲, 2003 .

A Sparse and Low-rank approach to efficient face alignment for photo-real talking head synthesis

Frank K. Soong, Yeung Yam, Lijuan Wang, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hierarchical stochastic feature matching for robust speech recognition

Chin-Hui Lee, Frank K. Soong, Hui Jiang, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Improved utterance rejection using length dependent thresholds

Frank K. Soong, Sunil K. Gupta, F. Soong, 1998, ICSLP.

On the use of instantaneous and transitional spectral information in speaker recognition

Frank K. Soong, Aaron E. Rosenberg, A. Rosenberg, 1988, IEEE Trans. Acoust. Speech Signal Process..

Tone information as a confidence measure for improving Cantonese LVCSR

Frank K. Soong, Tan Lee, Yao Qian, 2004, INTERSPEECH.

Sub-word unit talker verification using hidden Markov models

Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong, 1990, International Conference on Acoustics, Speech, and Signal Processing.

An HMM trajectory tiling (HTT) approach to high quality TTS

Zhi-Jie Yan, Frank K. Soong, Yi-Jian Wu, 2010, INTERSPEECH.

Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS pdf

Lei Xie, Frank K. Soong, Lei He, 2019, INTERSPEECH.

A MSD-HMM Approach to Pen Trajectory Modeling for Online Handwriting Recognition

Frank K. Soong, Peng Liu, Lei Ma, 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

Break index labeling of mandarin text via syntactic-to-prosodic tree mapping

Hai Zhao, Frank K. Soong, Yao Qian, 2012, 2012 8th International Symposium on Chinese Spoken Language Processing.

Optimizing baseforms for HMM-based speech recognition

Frank K. Soong, Torbjørn Svendsen, Heiko Purnhagen, 1995, EUROSPEECH.

Spoken Language Understanding of Human-Machine Conversations for Language Learning Applications

Frank K. Soong, Keelan Evanini, Rutuja Ubale, 2020, J. Signal Process. Syst..

High quality lip-sync animation for 3D photo-realistic talking head

Frank K. Soong, Lijuan Wang, Wei Han, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A KL Divergence and DNN-Based Approach to Voice Conversion without Parallel Training Sentences

Haifeng Li, Frank K. Soong, Feng-Long Xie, 2016, INTERSPEECH.

Symbol graph based discriminative training and rescoring for improved math symbol recognition

Frank K. Soong, Yu Shi, Zhen Xuan Luo, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Cross validation and Minimum Generation Error for improved model clustering in HMM-based TTS

Frank K. Soong, Yi-Jian Wu, Feng-Long Xie, 2012, 2012 8th International Symposium on Chinese Spoken Language Processing.

Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis

Frank K. Soong, Lei He, Yao Qian, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

High quality lips animation with speech and captured facial action unit as A/V input

Frank K. Soong, Lijuan Wang, Lijuan Wang, 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

Context constrained-generalized posterior probability for verifying phone transcriptions

Frank K. Soong, Lijuan Wang, Wenju Liu, 2007, INTERSPEECH.

Auto-Segmentation Based Partitioning and Clustering Approach to Robust Endpointing

Frank K. Soong, Yu Shi, Jian-Lai Zhou, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A Two-Pass Framework of Mispronunciation Detection and Diagnosis for Computer-Aided Pronunciation Training

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Perceptual annotation of expressive speech

Frank K. Soong, Yong Zhao, Lijuan Wang, 2007, SSW.

Agreement Learning for Automatic Accent Annotation

Ping Zhang, Frank K. Soong, Yong Zhao, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

On the use of transient information in speech recognition

Frank K. Soong, Jean-Sylvain Liénard, 1984, ICASSP.

A multi-space distribution (MSD) approach to speech recognition of tonal languages

Frank K. Soong, Jiqing Han, Jian-Lai Zhou, 2006, INTERSPEECH.

KL-divergence based mispronunciation detection via DNN and decision tree in the phonetic space

Frank K. Soong, Wenping Hu, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

A probabilistic acoustic map based discriminative HMM training

Frank K. Soong, Eng-Fong Huang, 1990, International Conference on Acoustics, Speech, and Signal Processing.

A data selection strategy for utterance verification in continuous speech recognition

Chin-Hui Lee, Frank K. Soong, Hui Jiang, 2001, INTERSPEECH.

Pitch transformation in neural network based voice conversion

Haifeng Li, Frank K. Soong, Yao Qian, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

A Cohort-Based Speaker Model Synthesis for Mismatched Channels in Speaker Verification

Thomas Fang Zheng, Wei Wu, Frank K. Soong, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Experiments in automatic talker verification using sub-word unit hidden Markov models

Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong, 1990, ICSLP.

Improved Prosody Generation by Maximizing Joint Probability of State and Longer Units

Zhizheng Wu, Frank K. Soong, Boyang Gao, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

A frequency-weighted Itakura spectral distortion measure and its application to speech recognition in noise

Frank K. Soong, Man Mohan Sondhi, 1988, IEEE Trans. Acoust. Speech Signal Process..

Training Discriminative HMM by Optimal Allocation of Gaussian Kernels

Zhi-Jie Yan, Frank K. Soong, Ren-Hua Wang, 2006 .

Exploring Sequential Characteristics in Speaker Bottleneck Feature for Text-Dependent Speaker Verification

Jie Li, Frank K. Soong, Liping Chen, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Evaluation of a vector quantization talker recognition system in text independent and text dependent modes

Aaron E. Rosenberg, Frank K. Soong, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Minimum divergence based discriminative training

Jun Du, Frank K. Soong, Peng Liu, 2006, INTERSPEECH.

Perceptual quality and modeling accuracy of excitation parameters in DLSTM-based speech synthesis systems

Frank K. Soong, Hong-Goo Kang, Eunwoo Song, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

On the asymptotic behavior of a complex adaptive line enchancer (CALE)

Frank K. Soong, Allen M. Peterson, S. Shankar Narayan, 1981, ICASSP.

Recognition of noisy speech using normalized moments

Frank K. Soong, Qi Li, Jingdong Chen, 2002, INTERSPEECH.

Discriminative acoustic model for improving mispronunciation detection and diagnosis in computer-aided pronunciation training (CAPT)

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2010, INTERSPEECH.

Robust verification of recognized words in noise

Satoshi Nakamura, Frank K. Soong, Wai Kit Lo, 2004, INTERSPEECH.

Paired Phone-Posteriors Approach to ESL Pronunciation Quality Assessment

Frank K. Soong, Wenping Hu, Yujia Xiao, 2018, INTERSPEECH.

Recent advancements in automatic speaker authentication

Biing-Hwang Juang, Chin-Hui Lee, Frank K. Soong, 1999, IEEE Robotics Autom. Mag..

Turning a Monolingual Speaker into Multilingual for a Mixed-language TTS

Frank K. Soong, Sheng Zhao, Ji He, 2012, INTERSPEECH.

s-Transformer: Segment-Transformer for Robust Neural Speech Synthesis pdf

Frank K. Soong, Xi Wang, Lei He, 2020, ArXiv.

Static and Dynamic Spectral Features: Their Noise Robustness and Optimal Weights for ASR

Chen Yang, Frank K. Soong, Tan Lee, 2007, IEEE Trans. Speech Audio Process..

Discriminative scoring for speaker recognition based on I-vectors

Thomas Fang Zheng, Jun Wang, Dong Wang, 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

A New Phonetic Candidate Generator for Improving Search Query Efficiency

Bo Zhang, Frank K. Soong, Bo Peng, 2011, INTERSPEECH.

Modeling Cantonese pronunciation variation by acoustic model refinement

Frank K. Soong, Tan Lee, Patgi Kam, 2003, INTERSPEECH.

An ellipsoid constrained quadratic programming perspective to discriminative training of HMMs

Frank K. Soong, Peng Liu, 2008, INTERSPEECH.

A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition

Frank K. Soong, Eng-Fong Huang, F. Soong, 1990, HLT.

Large vocabulary, word-based Mandarin dictation system

Frank K. Soong, Lin-Shan Lee, Jung-Kuei Chen, 1995, EUROSPEECH.

HMM-based motion trajectory generation for speech animation synthesis

Frank K. Soong, Lijuan Wang, Wei Han, 2009, AVSP.

Synthesizing photo-real talking head via trajectory-guided sample selection

Frank K. Soong, Lijuan Wang, Wei Han, 2010, INTERSPEECH.

A frame mapping based HMM approach to cross-lingual voice transformation

Frank K. Soong, Ji Xu, Yao Qian, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A high-performance auditory feature for robust speech recognition

Frank K. Soong, Qi Li, Olivier Siohan, 2000, INTERSPEECH.

DNN i-Vector Speaker Verification with Short, Text-Constrained Test Utterances

Frank K. Soong, Wenping Hu, Helen M. Meng, 2017, INTERSPEECH.

Improving Sub-Phone Modeling for Better Native Language Identification with Non-Native English Speech

Frank K. Soong, David Suendermann-Oeft, Keelan Evanini, 2017, INTERSPEECH.

Word embedding for recurrent neural network based TTS synthesis

Hai Zhao, Frank K. Soong, Lei He, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A New Glottal Neural Vocoder for Speech Synthesis

Xi Wang, Frank K. Soong, Yang Cui, 2018, INTERSPEECH.

Efficient handwriting correction of speech recognition errors with template constrained posterior (TCP)

Frank K. Soong, Peng Liu, Tao Hu, 2008, INTERSPEECH.

Sequence generation error (SGE) minimization based deep neural networks training for text-to-speech synthesis

Frank K. Soong, Lei He, Yao Qian, 2015, INTERSPEECH.

A KL divergence and DNN approach to cross-lingual TTS

Haifeng Li, Frank K. Soong, Feng-Long Xie, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Model-based speech separation: identifying transcription using orthogonality

Frank K. Soong, Tan Lee, Siu Wa Lee, 2009, INTERSPEECH.

A new DNN-based high quality pronunciation evaluation for computer-aided language learning (CALL)

Frank K. Soong, Wenping Hu, Yao Qian, 2013, INTERSPEECH.

Classifier design for verification of multi-class recognition decision

Biing-Hwang Juang, Frank K. Soong, Tomoko Matsui, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Performance of Discriminative HMM Training in Noise

Jun Du, Frank K. Soong, Peng Liu, 2007, Int. J. Comput. Linguistics Chin. Lang. Process..

An evidence framework for Bayesian learning of continuous-density hidden Markov models

Jen-Tzung Chien, Frank K. Soong, Yu Zhang, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Syllable Lattice Approach to Speaker Verification

Frank K. Soong, Chang Dong Yoo, Minho Jin, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

HMM trajectory-guided sample selection for photo-realistic talking head

Frank K. Soong, Lijuan Wang, 2014, Multimedia Tools and Applications.

Proficiency Assessment of ESL Learner's Sentence Prosody with TTS Synthesized Voice as Reference

Frank K. Soong, Yujia Xiao, F. Soong, 2017, INTERSPEECH.

A unified trajectory tiling approach to high quality TTS and cross-lingual voice transformation

Frank K. Soong, Yao Qian, 2012, 2012 8th International Symposium on Chinese Spoken Language Processing.

Syllable Lattice Based Re-Scoring For Speaker Verification

Frank K. Soong, Chang Dong Yoo, Minho Jin, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Noise estimation using a constrained sequential HMM IN log-spectral domain

Jianwu Dang, Yonghong Yan, Frank K. Soong, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automatic Speech and Speaker Recognition

Kuldip K. Paliwal, Chin-Hui Lee, Frank K. Soong, 1996 .

A cross-language state mapping approach to bilingual (Mandarin-English) TTS

Frank K. Soong, Hui Liang, Gongshen Liu, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

A segment model based approach to speech recognition

Frank K. Soong, Chin-Hui Lee, Bing-Hwang Juang, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Mispronunciation detection for Mandarin Chinese

Frank K. Soong, Feng Zhang, Chao Huang, 2008, INTERSPEECH.

A Unified Trajectory Tiling Approach to High Quality Speech Rendering

Zhi-Jie Yan, Frank K. Soong, Yao Qian, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

A minimum v/u error approach to F0 generation in HMM-based TTS

Zhizheng Wu, Frank K. Soong, Miaomiao Wang, 2009, INTERSPEECH.

A dynamic in-search discriminative training approach for large vocabulary speech recognition

Chin-Hui Lee, Frank K. Soong, Olivier Siohan, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The Paradigm for Creating Multi-lingual Text-To-Speech Voice Databases

Frank K. Soong, Yong Zhao, Yining Chen, 2006, ISCSLP.

Formant-based frequency warping for improving speaker adaptation in HMM TTS

Bo Zhang, Frank K. Soong, Yi-Jian Wu, 2010, INTERSPEECH.

ISCSLP 2004 Technical Program Committee

Pu-Jen Cheng, Yifan Gong, Frank K. Soong, 2004 .

Cepstral channel normalization techniques for HMM-based speaker verification

Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong, 1994, ICSLP.

Pitch accent detection and prediction with DCT features and CRF model

Frank K. Soong, Wenping Hu, Yao Qian, 2012, 2012 8th International Symposium on Chinese Spoken Language Processing.

An Efficient Subband Linear Prediction for LPCNet-Based Neural Synthesis

Frank K. Soong, Yang Cui, Xi Wang, 2020, INTERSPEECH.

Automatic Speech and Speaker Recognition: Advanced Topics

Kuldip K. Paliwal, Chin-Hui Lee, Frank K. Soong, 1999 .

HMM-Based Mixed-Language (Mandarin-English) Speech Synthesis

Frank K. Soong, Yao Qian, Houwei Cao, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

Weighted Likelihood Ratio (WLR) Hidden Markov Model for Noisy Speech Recognition

Frank K. Soong, Chao Huang, Jian-Lai Zhou, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A Unified Approach in Speech-to-Speech Translation: Integrating Features of Speech recognition and Machine Translation

Taro Watanabe, Frank K. Soong, Hirofumi Yamamoto, 2004, COLING.

A dynamic in-search data selection method with its applications to acoustic modeling and utterance verification

Chin-Hui Lee, Frank K. Soong, Hui Jiang, 2005, IEEE Transactions on Speech and Audio Processing.

Improving speaker verification performance against long-term speaker variability

Thomas Fang Zheng, Jun Wang, Frank K. Soong, 2016, Speech Commun..

Generalized posterior probability for minimum error verification of recognized sentences

Frank K. Soong, Wai Kit Lo, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network pdf

Hai Zhao, Frank K. Soong, Lei He, 2015, ArXiv.

Improved F0 modeling and generation in voice conversion

Nobuaki Minematsu, Frank K. Soong, Yao Qian, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Subband coding of speech using backward adaptive prediction and bit allocation

Frank K. Soong, N. Jayant, R. Cox, 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Text Driven 3D Photo-Realistic Talking Head

Frank K. Soong, Qiang Huo, Lijuan Wang, 2011, INTERSPEECH.

A Unified Framework for Symbol Segmentation and Recognition of Handwritten Mathematical Expressions

Frank K. Soong, Yu Shi, HaiYang Li, 2007 .

Optimal acoustic and language model weights for minimizing word verification errors

Satoshi Nakamura, Frank K. Soong, Wai Kit Lo, 2004, INTERSPEECH.

On noise robustness of dynamic and static features for continuous Cantonese digit recognition

Chen Yang, Frank K. Soong, Tan Lee, 2004, 2004 International Symposium on Chinese Spoken Language Processing.

A Multi-Space Distribution (MSD) and two-stream tone modeling approach to Mandarin speech recognition

Frank K. Soong, Yao Qian, 2009, Speech Commun..

Verification of Multi-Class Recognition Decision: A Classification Approach

Biing-Hwang Juang, Frank K. Soong, Tomoko Matsui, 2005, IEICE Trans. Inf. Syst..

An efficient vector-quantization preprocessor for speaker independent isolated word recognition

Frank K. Soong, Lawrence R. Rabiner, A. Bergh, 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Tone-enhanced generalized character posterior probability (GCPP) for Cantonese LVCSR

Frank K. Soong, Tan Lee, Yao Qian, 2008, Comput. Speech Lang..

Continuous probabilistic acoustic map for speaker identification

Frank K. Soong, A. E. Rosenberg, B. L. Tseng, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Feature reinforcement with word embedding and parsing information in neural TTS pdf

Frank K. Soong, Lei He, Huaiping Ming, 2019, ArXiv.

Static and Dynamic Spectral Features: Their Noise Robustness and Optimal Weights for ASR

Chen Yang, Frank K. Soong, Tan Lee, 2005, IEEE Transactions on Audio, Speech, and Language Processing.

Rendering a personalized photo-real talking head from short video footage

Frank K. Soong, Lijuan Wang, Wei Han, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

An N-best candidates-based discriminative training for speech recognition applications

Frank K. Soong, Jung-Kuei Chen, F. Soong, 1994, IEEE Trans. Speech Audio Process..

A constrained line search approach to general discriminative HMM training

Frank K. Soong, Peng Liu, Ren-Hua Wang, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

A perceptual study of acceleration parameters in HMM-based TTS

Zhi-Jie Yan, Frank K. Soong, Yining Chen, 2010, INTERSPEECH.

From Speech Signals to Semantics — Tagging Performance at Acoustic, Phonetic and Word Levels

Frank K. Soong, Keelan Evanini, Rutuja Ubale, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Generalization of the minimum classification error (MCE) training based on maximizing generalized posterior probability (GPP)

Biing-Hwang Juang, Frank K. Soong, Jian-Lai Zhou, 2006, INTERSPEECH.

Evaluating the Aurora connected digit recognition task - a bell labs approach

Chin-Hui Lee, Frank K. Soong, Qi Li, 2001, INTERSPEECH.

一般化事後確率を用いた異なるレベルの大語彙連続音声認識出力の検証(大語彙音声認識)(第6回音声言語シンポジウム)

Frank K. Soong, Wai Kit Lo, 中村哲, 2004 .

Automatic mispronunciation detection for Mandarin

Frank K. Soong, Ren-Hua Wang, Feng Zhang, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

GPU-accelerated Gaussian clustering for fMPE discriminative training

Frank K. Soong, Yu Shi, Frank Seide, 2008, INTERSPEECH.

On the high resolution and unbiased frequency estimates of sinusoids in white noise-A new adaptive approach

Frank K. Soong, Allen M. Peterson, A. Peterson, 1982, ICASSP.

An unsupervised approach to automatic prosodic annotation

Ping Zhang, Frank K. Soong, Yining Chen, 2007, INTERSPEECH.

Binocular photometric stereo acquisition and reconstruction for 3d talking head applications

Yasuyuki Matsushita, Frank K. Soong, Lijuan Wang, 2013, INTERSPEECH.

A tree-based kernel selection approach to efficient Gaussian mixture model-universal background model based speaker identification

Thomas Fang Zheng, Frank K. Soong, Zhanjiang Song, 2006, Speech Commun..

Improved prosody generation by maximizing joint likelihood of state and longer units

Zhizheng Wu, Frank K. Soong, Yao Qian, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Prosody for Mandarin speech recognition: a comparative study of read and spontaneous speech

Frank K. Soong, Tan Lee, Yao Qian, 2008, INTERSPEECH.

Modeling Cantonese Pronunciation Variations for Large-Vocabulary Continuous Speech Recognition

Frank K. Soong, Tan Lee, Patgi Kam, 2006, Int. J. Comput. Linguistics Chin. Lang. Process..

Graph-Based Partial Hypothesis Fusion for Pen-Aided Speech Input

Frank K. Soong, Peng Liu, F. Soong, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

Modeling pitch trajectory by hierarchical HMM with minimum generation error training

Frank K. Soong, Yi-Jian Wu, F. Soong, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Word recognition using whole word and subword models

Chin-Hui Lee, Frank K. Soong, Lawrence R. Rabiner, 1989, International Conference on Acoustics, Speech, and Signal Processing,.

Improving letter-to-sound conversion performance with automatically generated new words

Frank K. Soong, Yining Chen, Jia-Li You, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Report: A vector quantization approach to speaker recognition

Aaron E. Rosenberg, Frank K. Soong, Lawrence R. Rabiner, 1987, AT&T Technical Journal.

Line spectrum pair (LSP) and speech data compression

Biing-Hwang Juang, Frank K. Soong, B. Juang, 1984, ICASSP.

A minimum converted trajectory error (MCTE) approach to high quality speech-to-lips conversion

Frank K. Soong, Mark Hasegawa-Johnson, Xiaodan Zhuang, 2010, INTERSPEECH.

Improved spoken language translation using n-best speech recognition hypotheses

Taro Watanabe, Frank K. Soong, Eiichiro Sumita, 2004, INTERSPEECH.

A Unified Framework for Symbol Segmentation and Recognition of Handwritten Mathematical Expressions

Frank K. Soong, Yu Shi, HaiYang Li, 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

Fast least-squares (LS) in the voice echo cancellation application

Frank K. Soong, Allen M. Peterson, A. Peterson, 1982, ICASSP.

A Constrained Line Search Optimization Method for Discriminative Training of HMMs

Frank K. Soong, Peng Liu, Ren-Hua Wang, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

Modeling and Generating Tone Contour with Phrase Intonation for Mandarin Chinese Speech

Zhizheng Wu, Bo Zhang, Frank K. Soong, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

Hidden Markov models with divergence based vector quantized variances

Frank K. Soong, Jae H. Kim, Raziel Haimi-Cohen, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

A fast table lookup based, statistical model driven non-uniform unit selection TTS

Xiaobo Zhou, Frank K. Soong, Yao Qian, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Evaluation of a vector quantization talker recognition system in text independent and text dependent modes

Aaron E. Rosenberg, Frank K. Soong, 1987 .

Enrich Web Applications with Voice Internet Persona Text-to-Speech for Anyone, Anywhere

Frank K. Soong, Yusheng Li, Min Chu, 2007, HCI.

A MSD-HMM Approach to Pen Trajectory Modeling for Online Handwriting Recognition

Frank K. Soong, Lei Ma, Yi-Jian Wu, 2007 .

A New Minimum Divergence Approach to Discriminative Training

Jun Du, Frank K. Soong, Peng Liu, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

An orthogonal polynomial representation of speech signals and its probabilistic model for text independent speaker verification

Frank K. Soong, Hsiao-Chuan Wang, Chi-Shi Liu, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

An improved DNN-based approach to mispronunciation detection and diagnosis of L2 learners' speech

Frank K. Soong, Wenping Hu, Yao Qian, 2015, SLaTE.

Context-Dependent Boundary Model for Refining Boundaries Segmentation of TTS Units

Zhigang Cao, Frank K. Soong, Yong Zhao, 2006, IEICE Trans. Inf. Syst..

An auditory system-based feature for robust speech recognition

Frank K. Soong, Qi Li, Olivier Siohan, 2001, INTERSPEECH.

LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis pdf

Frank K. Soong, Hong-Goo Kang, Feng-Long Xie, 2018, 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

A Robust Voice Activity Detection Based on Noise Eigenspace Projection

Jianwu Dang, Frank K. Soong, Yu Shi, 2006, ISCSLP.

Continuous mixture HMM-LR using the a* algorithm for continuous speech recognition

Kenji Kita, Frank K. Soong, Shigeki Sagayama, 1992, ICSLP.

Auto-checking speech transcriptions by multiple template constrained posterior

Frank K. Soong, Lijuan Wang, Shenghao Qin, 2009, INTERSPEECH.

Speaker recognition based on source coding approaches

Biing-Hwang Juang, Frank K. Soong, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Capturing L2 segmental mispronunciations with joint-sequence models in Computer-Aided Pronunciation Training (CAPT)

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

Optimal quantization of LSP parameters using delayed decisions

Frank K. Soong, B.-H. Juang, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Background model based posterior probability for measuring confidence

Frank K. Soong, Ye Tian, Peng Liu, 2005, INTERSPEECH.

Synthesizing visual speech trajectory with minimum generation error

Frank K. Soong, Lijuan Wang, Xiaodan Zhuang, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

TTS synthesis with bidirectional LSTM based recurrent neural networks

Frank K. Soong, Yao Qian, Feng-Long Xie, 2014, INTERSPEECH.

Prefix tree based auto-completion for convenient bi-modal chinese character input

Frank K. Soong, Peng Liu, Lei Ma, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

AA spectral space warping approach to cross-lingual voice transformation in HMM-based TTS

Hao Wang, Frank K. Soong, Helen M. Meng, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The Use of DBN-HMMs for Mispronunciation Detection and Diagnosis in L2 English to Support Computer-Aided Pronunciation Training

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2012, INTERSPEECH.

RIch-context Unit Selection (RUS) approach to high quality TTS

Zhi-Jie Yan, Frank K. Soong, Yao Qian, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Word graph based speech rcognition error correction by handwriting input

Frank K. Soong, Peng Liu, F. Soong, 2006, ICMI '06.

Frequency estimation by linear prediction

Frank K. Soong, Donald W. Tufts, Rahul M. Rao, 1978, ICASSP.

GENERALIZED POSTERIOR PROBABILITY FOR VERIFYING RECOGNIZED WORDS OPTIMALLY IN MICROPHONE ARRAY APPLICATIONS

Satoshi Nakamura, Frank K. Soong, Wolfgang Herbordt, 2005 .

A vector-quantization-based preprocessor for speaker-independent isolated word recognition

Frank K. Soong, Lawrence R. Rabiner, Kuk-Chin Pan, 1985, IEEE Trans. Acoust. Speech Signal Process..

High performance connected digit recognition, using hidden Markov models

Frank K. Soong, Jay G. Wilpon, Lawrence R. Rabiner, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

A source-filter based adaptive harmonic model and its application to speech prosody modification

Frank K. Soong, Hong-Goo Kang, JeeSok Lee, 2013, INTERSPEECH.

Automatic Detection of Tone Mispronunciation in Mandarin

Frank K. Soong, Li Zhang, Chao Huang, 2006, ISCSLP.

Refining phoneme segmentations using speaker-adaptive context dependent boundary models

Zhigang Cao, Frank K. Soong, Yong Zhao, 2005, INTERSPEECH.

Iterative unit selection with unnatural prosody detection

Frank K. Soong, Yong Zhao, Jieyu Zhao, 2007, INTERSPEECH.

A hierarchical F0 modeling method for HMM-based speech synthesis

Frank K. Soong, Li-Rong Dai, Zhen-Hua Ling, 2010, INTERSPEECH.

A high quality subband speech coder with backward adaptive predictor and optimal time-frequency bit assignment

Frank K. Soong, N. Jayant, R. Cox, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Combining neighboring filter channels to improve quantile based histogram equalization

Hermann Ney, Frank K. Soong, Olivier Siohan, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

A Two-Pass Framework of Mispronunciation Detection and Diagnosis for Computer-Aided Pronunciation Training

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2016, IEEE ACM Trans. Audio Speech Lang. Process..

Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS

Frank K. Soong, Huaiping Ming, Lei He, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker and language factorization in DNN-based TTS synthesis

Frank K. Soong, Lei He, Yao Qian, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving native language (L1) identifation with better VAD and TDNN trained separately on native and non-native English corpora

Frank K. Soong, Keelan Evanini, Rutuja Ubale, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Objective Intelligibility Assessment of Text-to-Speech System using Template Constrained Generalized Posterior Probability

Frank K. Soong, Lijuan Wang, Zhe Geng, 2012, INTERSPEECH.

Tone-Enhanced Generalized Character Posterior Probability (GCPP) for Cantonese LVCSR

Frank K. Soong, Tan Lee, Yao Qian, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A Robust VAD Based Upon Noise Eigenspace Projection

Frank K. Soong, Yu Shi, Dongwen Ying, 2006 .

On Mispronunciation Lexicon Generation Using Joint-Sequence Multigrams in Computer-Aided Pronunciation Training (CAPT)

Frank K. Soong, Helen M. Meng, Xiaojun Qian, 2011, INTERSPEECH.

An Improved Frame-Unit-Selection Based Voice Conversion System Without Parallel Training Data

Frank K. Soong, Li Meng, Feng-Long Xie, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Distributed Word Representations For Bidirectional LSTM Recurrent Neural Network

Hai Zhao, Frank K. Soong, Lei He, 2016, NAACL.

A Comparative Study of Discriminative Methods for Reranking LVCSR N-Best Hypotheses in Domain Adaptation and Generalization

Frank K. Soong, Jianfeng Gao, Helen M. Meng, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A DNN-based acoustic modeling of tonal language and its application to Mandarin pronunciation training

Frank K. Soong, Wenping Hu, Yao Qian, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Measuring attribute dissimilarity with HMM KL-divergence for speech synthesis

Frank K. Soong, Yong Zhao, Xi Xiao, 2007, SSW.

Speaker verification method using group normalization scoring

Biing-Hwang Juang, Chin-Hui Lee, Frank K. Soong, 1993 .

Frame Selection in SI-DNN Phonetic Space with WaveNet Vocoder for Voice Conversion without Parallel Training Data

Frank K. Soong, Haifeng Li, Xi Wang, 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

A Cross-Language State Sharing and Mapping Approach to Bilingual (Mandarin–English) TTS

Frank K. Soong, Hui Liang, Yao Qian, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

Template constrained posterior for verifying phone transcriptions

Frank K. Soong, Tao Hu, Lijuan Wang, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice pdf

Frank K. Soong, Yan Deng, Lei He, 2018, ArXiv.

Signal Trajectory Based Noise Compensation for Robust Speech Recognition

Zhi-Jie Yan, Frank K. Soong, Ren-Hua Wang, 2006, ISCSLP.

Improved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone Models

Frank K. Soong, Jiqing Han, Jian-Lai Zhou, 2006, ISCSLP.

Rich context modeling for high quality HMM-based TTS

Zhi-Jie Yan, Frank K. Soong, Yao Qian, 2009, INTERSPEECH.

Bell labs approach to Aurora evaluation on connected digit recognition

Frank K. Soong, Qi Li, Jingdong Chen, 2002, INTERSPEECH.

Harmonic filtering for joint estimation of pitch and voiced source with single-microphone input

Frank K. Soong, Pak-Chung Ching, Siu Wa Lee, 2005, INTERSPEECH.

Improved minimum converted trajectory error training for real-time speech-to-lips conversion

Frank K. Soong, Lijuan Wang, Bo Yuan, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improved Chinese Character Input by Merging Speech and Handwriting Recognition Hypotheses

Frank K. Soong, Ye Tian, Xi Zhou, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A new Neural Network based logistic regression classifier for improving mispronunciation detection of L2 language learners

Frank K. Soong, Wenping Hu, Yao Qian, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

A vector quantization approach to speaker recognition

Biing-Hwang Juang, Frank K. Soong, Lawrence R. Rabiner, 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

A training procedure for a segment-based-network approach to isolated word recognition

Frank K. Soong, 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Divergence-Based Similarity Measure for Spoken Document Retrieval

Frank K. Soong, Peng Liu, Jian-Lai Zhou, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers

Yong Wang, Frank K. Soong, Yao Qian, 2015, Speech Commun..

Large vocabulary word recognition based on tree-trellis search

Frank K. Soong, Lin-Shan Lee, Jung-Kuei Chen, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Pitch Tracking for Model-Based Speech Separation

Frank K. Soong, Tan Lee, Pak-Chung Ching, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding pdf

Hai Zhao, Frank K. Soong, Lei He, 2015, ArXiv.

An HMM-Based Mandarin Chinese Text-To-Speech System

Frank K. Soong, Yining Chen, Min Chu, 2006, ISCSLP.

Photo-real lips synthesis with trajectory-guided sample selection

Frank K. Soong, Lijuan Wang, Wei Han, 2010, SSW.

The use of cohort normalized scores for speaker verification

Biing-Hwang Juang, Aaron E. Rosenberg, Chin-Hui Lee, 1992, ICSLP.

On divergence based clustering of normal distributions and its application to HMM adaptation

Frank K. Soong, Tor André Myrvoll, F. Soong, 2003, INTERSPEECH.

From text-to-speech (TTS) to talking head - a machine learning approach to A/V speech modeling and rendering

Frank K. Soong, Lijuan Wang, 2015, AVSP.

Unsupervised speaker adaptation for DNN-based TTS synthesis

Frank K. Soong, Lei He, Yao Qian, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Optimal clustering of multivariate normal distributions using divergence and its application to HMM adaptation

Frank K. Soong, Tor André Myrvoll, F. Soong, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

On the use of instantaneous and transitional spectral information in speaker recognition

Aaron E. Rosenberg, Frank K. Soong, A. Rosenberg, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Identifying Language Origin of Named Entity With Multiple Information Sources

Frank K. Soong, Yining Chen, Jia-Li You, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

Noisy Speech Recognition Performance of Discriminative HMMs

Jun Du, Frank K. Soong, Peng Liu, 2006, ISCSLP.

Statistical segmentation and word modeling techniques in isolated word recognition

Biing-Hwang Juang, Chin-Hui Lee, Frank K. Soong, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Generalized Segment Posterior Probability for Automatic Mandarin Pronunciation Evaluation

Frank K. Soong, Chao Huang, Jing Zheng, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Effective Spectral and Excitation Modeling Techniques for LSTM-RNN-Based Speech Synthesis Systems

Frank K. Soong, Hong-Goo Kang, Eunwoo Song, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A block least squares approach to acoustic echo cancellation

Biing-Hwang Juang, Frank K. Soong, Eric A. Woudenberg, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Integrating Hypotheses of Multiple Recognizers for Improving Mandarin LVCSR Performance

Frank K. Soong, Jian-Lai Zhou, Yu Shi, 2006 .

A real-time text to audio-visual speech synthesis system

Frank K. Soong, Yining Chen, Lei Ma, 2008, INTERSPEECH.

Photo-real talking head with deep bidirectional LSTM

Lei Xie, Frank K. Soong, Lijuan Wang, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge pdf

Frank K. Soong, Lei He, Mutian He, 2021, ArXiv.

Cycle consistent network for end-to-end style transfer TTS training

Frank K. Soong, Lei Xie, Lei He, 2021, Neural Networks.

Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS pdf

Frank K. Soong, Lei Xie, Xiaochun An, 2021, Interspeech.