Sheng Li

发表

Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview

Xiaojiao Chen, Sheng Li, Hao Huang, 2021, Applied Sciences.

System Description for Voice Privacy Challenge

M. Yoshikawa, Sheng Li, Yaowei Han, 2020 .

VOIS: The First Speech Therapy App Specifically Designed for Myanmar Hearing-Impaired Children

Nway Nway Han, Sheinn Thawtar Oo, Chenchen Ding, 2020, 2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA).

SpecMNet: Spectrum mend network for monaural speech enhancement

Zhao Lv, Xiao-pei Wu, J. Tao, 2022, Applied Acoustics.

Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection

Qianying Liu, Sheng Li, Jiyi Li, 2022, LREC.

Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer's Speech Detection

T. Shinozaki, Sheng Li, Longfei Yang, 2022, INTERSPEECH.

Relationship Between Speakers' Physiological Structure and Acoustic Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional Neural Network

J. Dang, M. Unoki, M. Akagi, 2022, 2022 30th European Signal Processing Conference (EUSIPCO).

Monaural Speech Enhancement Based on Spectrogram Decomposition for Convolutional Neural Network-sensitive Feature Extraction

J. Dang, Longbiao Wang, Tatsuya Kawahara, 2022, INTERSPEECH.

Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection

J. Dang, M. Unoki, M. Akagi, 2022, INTERSPEECH.

Subband-based Spectrogram Fusion for Speech Enhancement by Combining Mapping and Masking Approaches

J. Dang, Longbiao Wang, Tatsuya Kawahara, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

The Phoneme-Level Articulator Dynamics for Pronunciation Animation

Lan Wang, Sheng Li, En Qi, 2011, 2011 International Conference on Asian Language Processing.

Spectrograms Fusion with Minimum Difference Masks Estimation for Monaural Speech Dereverberation

Longbiao Wang, Jianwu Dang, Sheng Li, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-supervised ensemble DNN acoustic model training

Tatsuya Kawahara, Xugang Lu, Shinsuke Sakai, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Can We Train a Language Model Inside an End-to-End ASR Model? - Investigating Effective Implicit Language Modeling

D. Saito, N. Minematsu, Sheng Li, 2022, Conference on Algebraic Informatics.

Improving Transformer-Based Speech Recognition Systems with Compressed Structure and Speech Attributes Augmentation

Tatsuya Kawahara, Hisashi Kawai, Dabre Raj, 2019, INTERSPEECH.

Speech-Text Based Multi-Modal Training with Bidirectional Attention for Improved Speech Recognition

E. Chng, Sheng Li, Hao Huang, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Spectrograms Fusion-based End-to-end Robust Automatic Speech Recognition

J. Dang, Longbiao Wang, Tatsuya Kawahara, 2021, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition

S. Kurohashi, N. Minematsu, Fei Cheng, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Investigation of a Knowledge Distillation Method for CTC Acoustic Models

Hisashi Kawai, Ryoichi Takashima, Sheng Li, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Articulatory Attribute Modeling for Low-Resource Multilingual Speech Recognition

Tatsuya Kawahara, Hisashi Kawai, Sheng Li, 2019, INTERSPEECH.

An End-to-End Dialect Identification System with Transfer Learning from a Multilingual Automatic Speech Recognition Model

Xinhui Hu, Sheng Li, Ding Wang, 2021, Interspeech.

Finer-grained Modeling units-based Meta-Learning for Low-resource Tibetan Speech Recognition

J. Dang, Longbiao Wang, Sheng Li, 2022, INTERSPEECH.

Voice-Indistinguishability: Protecting Voiceprint In Privacy-Preserving Speech Data Release

Masatoshi Yoshikawa, Qiang Ma, Sheng Li, 2020, 2020 IEEE International Conference on Multimedia and Expo (ICME).

Investigation of Sequence-level Knowledge Distillation Methods for CTC Acoustic Models

Hisashi Kawai, Ryoichi Takashima, Sheng Li, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain

Ying Hu, Hao Huang, Sheng Li, 2021, Interspeech.

Voice-Indistinguishability -- Protecting Voiceprint with Differential Privacy under an Untrusted Server

Masatoshi Yoshikawa, Yang Cao, Sheng Li, 2020, CCS.

Towards Speech Dialogue Translation Mediating Speakers of Different Languages

Chenhui Chu, Sheng Li, National Institute of Information, 2023, 2305.09210.

Deep progressive multi-scale attention for acoustic event classification pdf

Yu Tsao, Hisashi Kawai, Sheng Li, 2019, ArXiv.

Fusion of Self-supervised Learned Models for MOS Prediction

Chenhui Chu, Raphaël Rubino, Sheng Li, 2022, INTERSPEECH.

System Description for the CN-Celeb Speaker Recognition Challenge 2022

Jichen Yang, Sheng Li, Hao Huang, 2022 .

Confidence estimation for speech recognition systems using conditional random fields trained with partially annotated data

Tatsuya Kawahara, Shinsuke Mori, Xugang Lu, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Semi-Supervised Acoustic Model Training by Discriminative Data Selection From Multiple ASR Systems’ Hypotheses

Tatsuya Kawahara, Yuya Akita, Sheng Li, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Speech Recognition Enhanced by Lightly-supervised and Semi-supervised Acoustic Model Training

Sheng Li, Sheng Li, 2016 .

Data selection from multiple ASR systems' hypotheses for unsupervised acoustic model training

Tatsuya Kawahara, Yuya Akita, Sheng Li, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automatic Lecture Transcription Based on Discriminative Data Selection for Lightly Supervised Acoustic Model Training

Tatsuya Kawahara, Yuya Akita, Sheng Li, 2015, IEICE Trans. Inf. Syst..

Knowledge Distillation-Based Representation Learning for Short-Utterance Spoken Language Identification

Hisashi Kawai, Sheng Li, Xugang Lu, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Cross-Lingual Transfer Learningfor End-to-End Speech Translation

S. Kurohashi, Chenhui Chu, Sheng Li, 2022, Journal of Natural Language Processing.

CTC Loss Function with a Unit-Level Ambiguity Penalty

Hisashi Kawai, Ryoichi Takashima, Sheng Li, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Temporal Attentive Pooling for Acoustic Event Detection

Yu Tsao, Hisashi Kawai, Xugang Lu, 2018, INTERSPEECH.

General or Specific? Investigating Effective Privacy Protection in Federated Learning for Speech Emotion Recognition

Sheng Li, Yang Cao, Masatoshi Yoshikawa, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement

Sheng Li, Xinkang Xu, Wangjin Zhou, 2023, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling

Jianwu Dang, Sheng Li, Lixin Pan, 2022, EURASIP Journal on Audio, Speech, and Music Processing.

Phoneme-level articulatory animation in pronunciation training

Hui Chen, Lan Wang, Helen M. Meng, 2012, Speech Commun..

Class-Wise Centroid Distance Metric Learning for Acoustic Event Detection

Hisashi Kawai, Sheng Li, Yu Tsao, 2019, INTERSPEECH.

Dialogue State Tracking with Sparse Local Slot Attention

T. Shinozaki, Sheng Li, Longfei Yang, 2023, NLP4CONVAI.

Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot Attention

T. Shinozaki, Sheng Li, Longfei Yang, 2023, ACL.

Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention

T. Shinozaki, Sheng Li, Longfei Yang, 2022, SIGDIAL.

MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction

Sheng Li, Raj Dabre, Wangjin Zhou, 2024, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).