Chongjia Ni

发表

Cross Attention with Monotonic Alignment for Speech Transformer

Chng Eng Siong, Shafiq R. Joty, Cheung-Chi Leung, 2020, INTERSPEECH.

I2CR: Improving Noise Robustness on Keyword Spotting using Inter-Intra Contrastive Regularization

Chng Eng Siong, Chong Zhang, Zhao Yang, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

From English pitch accent detection to Mandarin stress detection, where is the difference?

Bo Xu, Chongjia Ni, Wenju Liu, 2012, Comput. Speech Lang..

Automatic Prosodic Events Detection by Using Syllable-Based Acoustic, Lexical and Syntactic Features

Bo Xu, Chongjia Ni, Wenju Liu, 2011, INTERSPEECH.

Mandarin stress detection using syllable-based acoustic and syntactic features

Hua You, Chong-Jia Ni, Ai-Ying Zhang, 2010, 2010 International Conference on Audio, Language and Image Processing.

Mandarin stress detection using hierarchical model based boosting classification and regression tree

Bo Xu, Chongjia Ni, Wenju Liu, 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

Improved Large Vocabulary Mandarin Speech Recognition Using Prosodic and Lexical Information in Maximum Entropy Framework

Bo Xu, Wenju Liu, Chongjia Ni, 2009, 2009 Chinese Conference on Pattern Recognition.

Pitch Accent Prediction Using Ensemble Machine Learning

Chongjia Ni, Aiying Zhang, Chongjia Ni, 2009, 2009 Second International Conference on Intelligent Computation Technology and Automation.

Mandarin pitch accent prediction using hierarchical model based ensemble machine learning

Bo Xu, Wenju Liu, Chongjia Ni, 2009, 2009 IEEE Youth Conference on Information, Computing and Telecommunication.

Submodular Based Unsupervised Data Selection

Chongjia Ni, Ai-Ying Zhang, Chongjia Ni, 2018, IEICE Trans. Inf. Syst..

Cross-lingual deep neural network based submodular unbiased data selection for low-resource keyword search

Bin Ma, Haizhou Li, Cheung-Chi Leung, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Submodular data selection with acoustic and phonetic features for automatic speech recognition

Bin Ma, Cheung-Chi Leung, Chongjia Ni, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis

Bin Ma, Haizhou Li, Chng Eng Siong, 2016, INTERSPEECH.

System and keyword dependent fusion for spoken term detection

Haizhou Li, Chng Eng Siong, Haihua Xu, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Mandarin Stress Detection Using Acoustic, Lexical and Syntactic Features: Mandarin Stress Detection Using Acoustic, Lexical and Syntactic Features

Chong-Jia Ni, Ai-Ying Zhang, Wen-Ju Liu, 2011 .

Rapid Update of Multilingual Deep Neural Network for Low-Resource Keyword Search

Bin Ma, Haizhou Li, Cheung-Chi Leung, 2016, INTERSPEECH.

ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention

Chng Eng Siong, Trung Hieu Nguyen, Yukun Ma, 2023, ArXiv.

deHuBERT: Disentangling Noise in a Self-supervised Model for Robust Speech Recognition

E. Chng, Zhao Yang, Chongjia Ni, 2023, arXiv.org.

Independent Language Modeling Architecture for End-To-End ASR

Chng Eng Siong, Haihua Xu, Haizhou Li, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

De’hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition

E. Chng, Chongjia Ni, Dianwen Ng, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Contrastive Speech Mixup for Low-Resource Keyword Spotting

Trung Hieu Nguyen, E. Chng, Chong Zhang, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data pdf

Bin Ma, Chng Eng Siong, Haihua Xu, 2019, INTERSPEECH.

Preventing Early Endpointing for Online Automatic Speech Recognition

Bin Ma, Chng Eng Siong, Shafiq R. Joty, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Long short-term memory recurrent neural network based segment features for music genre classification

Wei Xue, Chongjia Ni, Wenju Liu, 2016, 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP).

Low-resource spoken keyword search strategies in georgian inspired by distinctive feature theory

Chng Eng Siong, Haihua Xu, Haizhou Li, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Investigate automatic speech recognition and keyword search for very low-resource language

Chongjia Ni, Bin Ma, B. Ma, 2017, 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP).

Low-resource keyword search strategies for tamil

Bin Ma, Haizhou Li, Chng Eng Siong, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Using prosody to improve Mandarin automatic speech recognition

Bo Xu, Chongjia Ni, Wenju Liu, 2010, INTERSPEECH.

A Unified Speaker Adaptation Approach for ASR pdf

Bin Ma, Chng Eng Siong, Shafiq R. Joty, 2021, EMNLP.

Automatic Prosodic Break Detection and Feature Analysis

Bo Xu, Wenju Liu, Chongjia Ni, 2012, Journal of Computer Science and Technology.

The Comparison between Mandarin Break Detection and English Break Detection

Chongjia Ni, Ai-Ying Zhang, Chongjia Ni, 2012, CCPR.