| 2023 | Interspeech | ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading. | Yujia Xiao, Shaofei Zhang, Xi Wang, Xu Tan, Lei He, Sheng Zhao, Frank K. Soong, Tan Lee |
| 2022 | ICASSP | A Universal Ordinal Regression for Assessing Phoneme-Level Pronunciation. | Shaoguang Mao, Frank K. Soong, Yan Xia, Jonathan Tien |
| 2022 | ICASSP | Improving Fastspeech TTS with Efficient Self-Attention and Compact Feed-Forward Network. | Yujia Xiao, Xi Wang, Lei He, Frank K. Soong |
| 2022 | ICASSP | An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings. | Wenxuan Ye, Shaoguang Mao, Frank K. Soong, Wenshan Wu, Yan Xia, Jonathan Tien, Zhiyong Wu |
| 2022 | Interspeech | Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge. | Mutian He, Jingzhou Yang, Lei He, Frank K. Soong |
| 2022 | Interspeech | A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS. | Haohan Guo, Feng-Long Xie, Frank K. Soong, Xixin Wu, Helen Meng |
| 2021 | ICASSP | Speech Bert Embedding for Improving Prosody in Neural TTS. | Liping Chen, Yan Deng, Xi Wang, Frank K. Soong, Lei He |
| 2021 | ICASSP | MBNET: MOS Prediction for Synthesized Speech with Mean-Bias Network. | Yichong Leng, Xu Tan, Sheng Zhao, Frank K. Soong, Xiang-Yang Li, Tao Qin |
| 2021 | ICASSP | Improving Pronunciation Assessment Via Ordinal Regression with Anchored Reference Samples. | Bin Su, Shaoguang Mao, Frank K. Soong, Yan Xia, Jonathan Tien, Zhiyong Wu |
| 2021 | ICASSP | A New High Quality Trajectory Tiling Based Hybrid TTS In Real Time. | Feng-Long Xie, Xinhui Li, Wen-Chao Su, Li Lu, Frank K. Soong |
| 2021 | Interspeech | Improving Performance of Seen and Unseen Speech Style Transfer in End-to-End Neural TTS. | Xiaochun An, Frank K. Soong, Lei Xie |
| 2020 | ICASSP | Improving LPCNET-Based Text-to-Speech with Linear Prediction-Structured Mixture Density Network. | Min-Jae Hwang, Eunwoo Song, Ryuichi Yamamoto, Frank K. Soong, Hong-Goo Kang |
| 2020 | ICASSP | Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS. | Yujia Xiao, Lei He, Huaiping Ming, Frank K. Soong |
| 2020 | ICASSP | An Improved Frame-Unit-Selection Based Voice Conversion System Without Parallel Training Data. | Feng-Long Xie, Xinhui Li, Bo Liu, Yibin Zheng, Li Meng, Li Lu, Frank K. Soong |
| 2020 | Interspeech | An Efficient Subband Linear Prediction for LPCNet-Based Neural Synthesis. | Yang Cui, Xi Wang, Lei He, Frank K. Soong |
| 2020 | Interspeech | Transfer Learning for Improving Singing-Voice Detection in Polyphonic Instrumental Music. | Yuanbo Hou, Frank K. Soong, Jian Luan, Shengchen Li |
| 2019 | ICASSP | Domain Adversarial Training for Improving Keyword Spotting Performance of ESL Speech. | Jingyong Hou, Pengcheng Guo, Sining Sun, Frank K. Soong, Wenping Hu, Lei Xie |
| 2019 | ICASSP | NN-based Ordinal Regression for Assessing Fluency of ESL Speech. | Shaoguang Mao, Zhiyong Wu, Jingshuai Jiang, Peiyun Liu, Frank K. Soong |
| 2019 | ICASSP | A Pitch-aware Approach to Single-channel Speech Separation. | Ke Wang, Frank K. Soong, Lei Xie |
| 2019 | Interspeech | A New GAN-Based End-to-End TTS Training Algorithm. | Haohan Guo, Frank K. Soong, Lei He, Lei Xie |
| 2019 | Interspeech | Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS. | Haohan Guo, Frank K. Soong, Lei He, Lei Xie |
| 2019 | Interspeech | Forward-Backward Decoding for Regularizing End-to-End TTS. | Yibin Zheng, Xi Wang, Lei He, Shifeng Pan, Frank K. Soong, Zhengqi Wen, Jianhua Tao |
| 2018 | ICASSP | Exploring Sequential Characteristics in Speaker Bottleneck Feature for Text-Dependent Speaker Verification. | Liping Chen, Yong Zhao, Shi-Xiong Zhang, Jie Li, Guoli Ye, Frank K. Soong |
| 2018 | Interspeech | A New Glottal Neural Vocoder for Speech Synthesis. | Yang Cui, Xi Wang, Lei He, Frank K. Soong |
| 2018 | Interspeech | Paired Phone-Posteriors Approach to ESL Pronunciation Quality Assessment. | Yujia Xiao, Frank K. Soong, Wenping Hu |
| 2017 | ASRU | Improving native language (L1) identifation with better VAD and TDNN trained separately on native and non-native English corpora. | Yao Qian, Keelan Evanini, Patrick L. Lange, Robert A. Pugh, Rutuja Ubale, Frank K. Soong |
| 2017 | ASRU | Perceptual quality and modeling accuracy of excitation parameters in DLSTM-based speech synthesis systems. | Eunwoo Song, Frank K. Soong, Hong-Goo Kang |
| 2017 | Interspeech | Improving Sub-Phone Modeling for Better Native Language Identification with Non-Native English Speech. | Yao Qian, Keelan Evanini, Xinhao Wang, David Suendermann-Oeft, Robert A. Pugh, Patrick L. Lange, Hillary R. Molloy, Frank K. Soong |
| 2017 | Interspeech | Proficiency Assessment of ESL Learner's Sentence Prosody with TTS Synthesized Voice as Reference. | Yujia Xiao, Frank K. Soong |
| 2017 | Interspeech | DNN i-Vector Speaker Verification with Short, Text-Constrained Test Utterances. | Jinghua Zhong, Wenping Hu, Frank K. Soong, Helen Meng |
| 2016 | ICASSP | Unsupervised speaker adaptation for DNN-based TTS synthesis. | Yuchen Fan, Yao Qian, Frank K. Soong, Lei He |
| 2016 | ICASSP | Speaker and language factorization in DNN-based TTS synthesis. | Yuchen Fan, Yao Qian, Frank K. Soong, Lei He |
| 2016 | ICASSP | A KL divergence and DNN approach to cross-lingual TTS. | Feng-Long Xie, Frank K. Soong, Haifeng Li |
| 2016 | Interspeech | Improved Time-Frequency Trajectory Excitation Vocoder for DNN-Based Speech Synthesis. | Eunwoo Song, Frank K. Soong, Hong-Goo Kang |
| 2016 | Interspeech | A KL Divergence and DNN-Based Approach to Voice Conversion without Parallel Training Sentences. | Feng-Long Xie, Frank K. Soong, Haifeng Li |
| 2016 | NAACL | Learning Distributed Word Representations For Bidirectional LSTM Recurrent Neural Network. | Peilu Wang, Yao Qian, Frank K. Soong, Lei He, Hai Zhao |
| 2015 | ICASSP | Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis. | Yuchen Fan, Yao Qian, Frank K. Soong, Lei He |
| 2015 | ICASSP | Photo-real talking head with deep bidirectional LSTM. | Bo Fan, Lijuan Wang, Frank K. Soong, Lei Xie |
| 2015 | ICASSP | Word embedding for recurrent neural network based TTS synthesis. | Peilu Wang, Yao Qian, Frank K. Soong, Lei He, Hai Zhao |
| 2015 | ICASSP | AA spectral space warping approach to cross-lingual voice transformation in HMM-based TTS. | Hao Wang, Frank K. Soong, Helen Meng |
| 2015 | Interspeech | Sequence generation error (SGE) minimization based deep neural networks training for text-to-speech synthesis. | Yuchen Fan, Yao Qian, Frank K. Soong, Lei He |
| 2014 | ICASSP | A DNN-based acoustic modeling of tonal language and its application to Mandarin pronunciation training. | Wenping Hu, Yao Qian, Frank K. Soong |
| 2014 | ICASSP | On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis. | Yao Qian, Yuchen Fan, Wenping Hu, Frank K. Soong |
| 2014 | ICASSP | A maximum a Posterior-based reconstruction approach to speech bandwidth expansion in noise. | Hyunson Seo, Hong-Goo Kang, Frank K. Soong |
| 2014 | Interspeech | TTS synthesis with bidirectional LSTM based recurrent neural networks. | Yuchen Fan, Yao Qian, Feng-Long Xie, Frank K. Soong |
| 2014 | Interspeech | Sequence error (SE) minimization training of neural network for voice conversion. | Feng-Long Xie, Yao Qian, Yuchen Fan, Frank K. Soong, Haifeng Li |
| 2014 | Interspeech | Modeling DCT parameterized F0 trajectory at intonation phrase level with DNN or decision tree. | Xiang Yin, Ming Lei, Yao Qian, Frank K. Soong, Lei He, Zhen-Hua Ling, Li-Rong Dai |
| 2013 | ICASSP | A fast table lookup based, statistical model driven non-uniform unit selection TTS. | Yao Qian, Frank K. Soong, Xiaobo Zhou, Yundi Qian, Xiaotian Zhang |
| 2013 | Interspeech | A new DNN-based high quality pronunciation evaluation for computer-aided language learning (CALL). | Wenping Hu, Yao Qian, Frank K. Soong |
| 2013 | Interspeech | A source-filter based adaptive harmonic model and its application to speech prosody modification. | JeeSok Lee, Frank K. Soong, Hong-Goo Kang |
| 2013 | Interspeech | Binocular photometric stereo acquisition and reconstruction for 3d talking head applications. | Chaoyang Wang, Lijuan Wang, Yasuyuki Matsushita, Bojun Huang, Magnetro Chen, Frank K. Soong |
| 2013 | Interspeech | A new language independent, photo-realistic talking head driven by voice only. | Xinjian Zhang, Lijuan Wang, Gang Li, Frank Seide, Frank K. Soong |
| 2012 | ICASSP | Improved minimum converted trajectory error training for real-time speech-to-lips conversion. | Wei Han, Lijuan Wang, Frank K. Soong, Bo Yuan |
| 2012 | ICASSP | High quality lip-sync animation for 3D photo-realistic talking head. | Lijuan Wang, Wei Han, Frank K. Soong |
| 2012 | ICASSP | Modeling pitch trajectory by hierarchical HMM with minimum generation error training. | Yi-Jian Wu, Frank K. Soong |
| 2012 | ICASSP | Noise estimation using a constrained sequential HMM IN log-spectral domain. | Dongwen Ying, Xugang Lu, Junfeng Li, Yonghong Yan, Jianwu Dang, Frank K. Soong |
| 2012 | Interspeech | Turning a Monolingual Speaker into Multilingual for a Mixed-language TTS. | Ji He, Yao Qian, Frank K. Soong, Sheng Zhao |
| 2012 | Interspeech | The Use of DBN-HMMs for Mispronunciation Detection and Diagnosis in L2 English to Support Computer-Aided Pronunciation Training. | Xiaojun Qian, Helen M. Meng, Frank K. Soong |
| 2012 | Interspeech | Objective Intelligibility Assessment of Text-to-Speech System using Template Constrained Generalized Posterior Probability. | Linfang Wang, Lijuan Wang, Yan Teng, Zhe Geng, Frank K. Soong |
| 2012 | Interspeech | Constrained Multichannel Speech Dereverberation. | Meng Yu, Frank K. Soong |
| 2011 | ICASSP | Improved F0 modeling and generation in voice conversion. | Aki Kunikoshi, Yao Qian, Frank K. Soong, Nobuaki Minematsu |
| 2011 | ICASSP | Speaker characterization using spectral subband energy ratio based on Harmonic plus Noise Model. | Yanhua Long, Zhi-Jie Yan, Frank K. Soong, Li-Rong Dai, Wu Guo |
| 2011 | ICASSP | A frame mapping based HMM approach to cross-lingual voice transformation. | Yao Qian, Ji Xu, Frank K. Soong |
| 2011 | ICASSP | Synthesizing visual speech trajectory with minimum generation error. | Lijuan Wang, Yi-Jian Wu, Xiaodan Zhuang, Frank K. Soong |
| 2011 | ICASSP | A Sparse and Low-rank approach to efficient face alignment for photo-real talking head synthesis. | King Keung Wu, Lijuan Wang, Frank K. Soong, Yeung Yam |
| 2011 | Interspeech | Improvements in Speaker Characterization Using Spectral Subband Energy Based on Harmonic plus Noise Model. | Yanhua Long, Zhi-Jie Yan, Frank K. Soong, Li-Rong Dai, Wu Guo |
| 2011 | Interspeech | A New Phonetic Candidate Generator for Improving Search Query Efficiency. | Bo Peng, Yao Qian, Frank K. Soong, Bo Zhang |
| 2011 | Interspeech | On Mispronunciation Lexicon Generation Using Joint-Sequence Multigrams in Computer-Aided Pronunciation Training (CAPT). | Xiaojun Qian, Helen M. Meng, Frank K. Soong |
| 2011 | Interspeech | Text Driven 3D Photo-Realistic Talking Head. | Lijuan Wang, Wei Han, Frank K. Soong, Qiang Huo |
| 2010 | ICASSP | RIch-context Unit Selection (RUS) approach to high quality TTS. | Zhi-Jie Yan, Yao Qian, Frank K. Soong |
| 2010 | ICASSP | Improved modeling for F0 generation and V/U decision in HMM-based TTS. | Qingqing Zhang, Frank K. Soong, Yao Qian, Zhijie Yan, Jielin Pan, Yonghong Yan |
| 2010 | ICASSP | Cross-validation based decision tree clustering for HMM-based TTS. | Yu Zhang, Zhi-Jie Yan, Frank K. Soong |
| 2010 | Interspeech | A perceptual study of acceleration parameters in HMM-based TTS. | Yining Chen, Zhi-Jie Yan, Frank K. Soong |
| 2010 | Interspeech | A hierarchical F0 modeling method for HMM-based speech synthesis. | Ming Lei, Yi-Jian Wu, Frank K. Soong, Zhen-Hua Ling, Li-Rong Dai |
| 2010 | Interspeech | Discriminative acoustic model for improving mispronunciation detection and diagnosis in computer-aided pronunciation training (CAPT). | Xiaojun Qian, Frank K. Soong, Helen M. Meng |
| 2010 | Interspeech | An HMM trajectory tiling (HTT) approach to high quality TTS. | Yao Qian, Zhi-Jie Yan, Yi-Jian Wu, Frank K. Soong, Xin Zhuang, Shengyi Kong |
| 2010 | Interspeech | Synthesizing photo-real talking head via trajectory-guided sample selection. | Lijuan Wang, Xiaojun Qian, Wei Han, Frank K. Soong |
| 2010 | Interspeech | Formant-based frequency warping for improving speaker adaptation in HMM TTS. | Xin Zhuang, Yao Qian, Frank K. Soong, Yi-Jian Wu, Bo Zhang |
| 2010 | Interspeech | A minimum converted trajectory error (MCTE) approach to high quality speech-to-lips conversion. | Xiaodan Zhuang, Lijuan Wang, Frank K. Soong, Mark Hasegawa-Johnson |
| 2009 | ICASSP | Improving mispronunciation detection using machine learning. | Yuqiang Chen, Chao Huang, Frank K. Soong |
| 2009 | ICASSP | State mapping for cross-language speaker adaptation in TTS. | Yining Chen, Yang Jiao, Yao Qian, Frank K. Soong |
| 2009 | ICASSP | Improved prosody generation by maximizing joint likelihood of state and longer units. | Yao Qian, Zhizheng Wu, Frank K. Soong |
| 2009 | ICASSP | An evidence framework for Bayesian learning of continuous-density hidden Markov models. | Yu Zhang, Peng Liu, Jen-Tzung Chien, Frank K. Soong |
| 2009 | Interspeech | Model-based speech separation: identifying transcription using orthogonality. | Siu Wa Lee, Frank K. Soong, Tan Lee |
| 2009 | Interspeech | A minimum v/u error approach to F0 generation in HMM-based TTS. | Yao Qian, Frank K. Soong, Miaomiao Wang, Zhizheng Wu |
| 2009 | Interspeech | Auto-checking speech transcriptions by multiple template constrained posterior. | Lijuan Wang, Shenghao Qin, Frank K. Soong |
| 2009 | Interspeech | Rich context modeling for high quality HMM-based TTS. | Zhi-Jie Yan, Yao Qian, Frank K. Soong |
| 2008 | ICASSP | Discriminative training for improving letter-to-sound conversion performance. | Yining Chen, Peng Liu, Jia-Li You, Frank K. Soong |
| 2008 | ICASSP | A cross-language state mapping approach to bilingual (Mandarin-English) TTS. | Hui Liang, Yao Qian, Frank K. Soong, Gongshen Liu |
| 2008 | ICASSP | Prefix tree based auto-completion for convenient bi-modal chinese character input. | Peng Liu, Lei Ma, Frank K. Soong |
| 2008 | ICASSP | Symbol graph based discriminative training and rescoring for improved math symbol recognition. | Zhen Xuan Luo, Yu Shi, Frank K. Soong |
| 2008 | ICASSP | Template constrained posterior for verifying phone transcriptions. | Lijuan Wang, Tao Hu, Frank K. Soong |
| 2008 | ICASSP | Improving letter-to-sound conversion performance with automatically generated new words. | Jia-Li You, Yining Chen, Frank K. Soong, Jin-Lin Wang |
| 2008 | ICASSP | Automatic mispronunciation detection for Mandarin. | Feng Zhang, Chao Huang, Frank K. Soong, Min Chu, Ren-Hua Wang |
| 2008 | ICPR | Radical based fine trajectory HMMs of online handwritten characters. | Peng Liu, Lei Ma, Frank K. Soong |
| 2008 | ICPR | A symbol graph based handwritten math expression recognition. | Yu Shi, Frank K. Soong |
| 2008 | Interspeech | Duration refinement by jointly optimizing state and longer unit likelihood. | Boyang Gao, Yao Qian, Zhizheng Wu, Frank K. Soong |
| 2008 | Interspeech | Mispronunciation detection for Mandarin Chinese. | Chao Huang, Feng Zhang, Frank K. Soong, Min Chu |
| 2008 | Interspeech | An ellipsoid constrained quadratic programming perspective to discriminative training of HMMs. | Peng Liu, Frank K. Soong |
| 2008 | Interspeech | Generating natural F0 trajectory with additive trees. | Yao Qian, Hui Liang, Frank K. Soong |
| 2008 | Interspeech | GPU-accelerated Gaussian clustering for fMPE discriminative training. | Yu Shi, Frank Seide, Frank K. Soong |
| 2008 | Interspeech | Efficient handwriting correction of speech recognition errors with template constrained posterior (TCP). | Lijuan Wang, Tao Hu, Peng Liu, Frank K. Soong |
| 2008 | Interspeech | A real-time text to audio-visual speech synthesis system. | Lijuan Wang, Xiaojun Qian, Lei Ma, Yao Qian, Yining Chen, Frank K. Soong |
| 2008 | Interspeech | Prosody for Mandarin speech recognition: a comparative study of read and spontaneous speech. | Yu Ting Yeung, Yao Qian, Tan Lee, Frank K. Soong |
| 2007 | ASRU | A constrained line search approach to general discriminative HMM training. | Peng Liu, Cong Liu, Hui Jiang, Frank K. Soong, Ren-Hua Wang |
| 2007 | HCI | Enrich Web Applications with Voice Internet Persona Text-to-Speech for Anyone, Anywhere. | Min Chu, Yusheng Li, Xin Zou, Frank K. Soong |
| 2007 | ICASSP | Divergence-Based Similarity Measure for Spoken Document Retrieval. | Peng Liu, Frank K. Soong, Jian-Lai Zhou |
| 2007 | ICASSP | A New Minimum Divergence Approach to Discriminative Training. | Jun Du, Peng Liu, Hui Jiang, Frank K. Soong, Ren-Hua Wang |
| 2007 | ICASSP | A Constrained Line Search Optimization for Discriminative Training in Speech Recognition. | Cong Liu, Peng Liu, Hui Jiang, Frank K. Soong, Ren-Hua Wang |
| 2007 | ICASSP | Agreement Learning for Automatic Accent Annotation. | Xinqiang Ni, Yining Chen, Min Chu, Frank K. Soong, Yong Zhao, Ping Zhang |
| 2007 | ICASSP | Full HMM Training for Minimizing Generation Error in Synthesis. | Yi-Jian Wu, Ren-Hua Wang, Frank K. Soong |
| 2007 | ICASSP | A Segmentation Posterior Based Endpointing Algorithm. | Yanlu Xie, Yu Shi, Frank K. Soong, Beiqian Dai |
| 2007 | ICASSP | Word Graph Based Feature Enhancement for Noisy Speech Recognition. | Zhi-Jie Yan, Frank K. Soong, Ren-Hua Wang |
| 2007 | ICASSP | Generalized Segment Posterior Probability for Automatic Mandarin Pronunciation Evaluation. | Jing Zheng, Chao Huang, Min Chu, Frank K. Soong, Weiping Ye |
| 2007 | ICDAR | A MSD-HMM Approach to Pen Trajectory Modeling for Online Handwriting Recognition. | Lei Ma, Frank K. Soong, Peng Liu, Yi-Jian Wu |
| 2007 | ICDAR | A Unified Framework for Symbol Segmentation and Recognition of Handwritten Mathematical Expressions. | Yu Shi, HaiYang Li, Frank K. Soong |
| 2007 | ICDAR | Minimum Error Discriminative Training for Radical-Based Online Chinese Handwriting Recognition. | Yu Zhang, Peng Liu, Frank K. Soong |
| 2007 | Interspeech | Model-based speech separation with single-microphone input. | Siu Wa Lee, Frank K. Soong, Pak-Chung Ching |
| 2007 | Interspeech | Iterative unit selection with unnatural prosody detection. | Dacheng Lin, Yong Zhao, Frank K. Soong, Min Chu, Jieyu Zhao |
| 2007 | Interspeech | An unsupervised approach to automatic prosodic annotation. | Xinqiang Ni, Yining Chen, Frank K. Soong, Min Chu, Ping Zhang |
| 2007 | Interspeech | Robust F0 modeling for Mandarin speech recognition in noise. | Sheng Qiang, Yao Qian, Frank K. Soong, Congfu Xu |
| 2007 | Interspeech | Context constrained-generalized posterior probability for verifying phone transcriptions. | Hua Zhang, Lijuan Wang, Frank K. Soong, Wenju Liu |
| 2006 | ICASSP | Weighted Likelihood Ratio (WLR) Hidden Markov Model for Noisy Speech Recognition. | Chao Huang, Yingchun Huang, Frank K. Soong, Jianlai Zhou |
| 2006 | ICASSP | Syllable Lattice Based Re-Scoring For Speaker Verification. | Minho Jin, Frank K. Soong, Chang D. Yoo |
| 2006 | ICASSP | An Iterative Trajectory Regeneration Algorithm for Separating Mixed Speech Sources. | Siu Wa Lee, Frank K. Soong, Pak-Chung Ching |
| 2006 | ICASSP | Tone-Enhanced Generalized Character Posterior Probability (GCPP) for Cantonese LVCSR. | Yao Qian, Frank K. Soong, Tan Lee |
| 2006 | ICASSP | Auto-Segmentation Based Partitioning and Clustering Approach to Robust Endpointing. | Yu Shi, Frank K. Soong, Jian-Lai Zhou |
| 2006 | ICASSP | A Comparative Study of Discriminative Methods for Reranking LVCSR N-Best Hypotheses in Domain Adaptation and Generalization. | Zhengyu Zhou, Jianfeng Gao, Frank K. Soong, Helen Meng |
| 2006 | ICASSP | Improved Chinese Character Input by Merging Speech and Handwriting Recognition Hypotheses. | Xi Zhou, Ye Tian, Jian-Lai Zhou, Frank K. Soong, Beiqian Dai |
| 2006 | ICMI | Word graph based speech rcognition error correction by handwriting input. | Peng Liu, Frank K. Soong |
| 2006 | Interspeech | Minimum divergence based discriminative training. | Jun Du, Peng Liu, Frank K. Soong, Jian-Lai Zhou, Ren-Hua Wang |
| 2006 | Interspeech | Generalization of the minimum classification error (MCE) training based on maximizing generalized posterior probability (GPP). | Qiang Fu, Antonio Moreno-Daniel, Biing-Hwang Juang, Jian-Lai Zhou, Frank K. Soong |
| 2006 | Interspeech | Auto-segmentation based VAD for robust ASR. | Yu Shi, Frank K. Soong, Jian-Lai Zhou |
| 2006 | Interspeech | A multi-space distribution (MSD) approach to speech recognition of tonal languages. | Huanliang Wang, Yao Qian, Frank K. Soong, Jian-Lai Zhou, Jiqing Han |
| 2005 | ICASSP | Optimal Clustering and Non-Uniform Allocation of Gaussian Kernels in Scalar Dimension for HMM Compression. | Xiao-Bing Li, Frank K. Soong, Tor Andr Myrvoll, Ren-Hua Wang |
| 2005 | ICASSP | Generalized Posterior Probability for Minimum Error Verification of Recognized Sentences. | Wai Kit Lo, Frank K. Soong |
| 2005 | ICASSP | Static and Dynamic Spectral Features: Their Noise Robustness and Optimal Weights for ASR. | Chen Yang, Frank K. Soong, Tan Lee |
| 2005 | Interspeech | Harmonic filtering for joint estimation of pitch and voiced source with single-microphone input. | Siu Wa Lee, Frank K. Soong, Pak-Chung Ching |
| 2005 | Interspeech | Background model based posterior probability for measuring confidence. | Peng Liu, Ye Tian, Jian-Lai Zhou, Frank K. Soong |
| 2005 | Interspeech | Phonetic transcription verification with generalized posterior probability. | Lijuan Wang, Yong Zhao, Min Chu, Frank K. Soong, Zhigang Cao |
| 2005 | Interspeech | Refining phoneme segmentations using speaker-adaptive context dependent boundary models. | Yong Zhao, Lijuan Wang, Min Chu, Frank K. Soong, Zhigang Cao |
| 2004 | COLING | A Unified Approach in Speech-to-Speech Translation: Integrating Features of Speech recognition and Machine Translation. | Ruiqiang Zhang, Gen-ichiro Kikui, Hirofumi Yamamoto, Frank K. Soong, Taro Watanabe, Wai Kit Lo |
| 2004 | Interspeech | Robust verification of recognized words in noise. | Wai Kit Lo, Frank K. Soong, Satoshi Nakamura |
| 2004 | Interspeech | Tone information as a confidence measure for improving Cantonese LVCSR. | Yao Qian, Tan Lee, Frank K. Soong |
| 2004 | Interspeech | Optimal acoustic and language model weights for minimizing word verification errors. | Frank K. Soong, Wai Kit Lo, Satoshi Nakamura |
| 2004 | Interspeech | Improved spoken language translation using n-best speech recognition hypotheses. | Ruiqiang Zhang, Gen-ichiro Kikui, Hirofumi Yamamoto, Frank K. Soong, Taro Watanabe, Eiichiro Sumita, Wai Kit Lo |
| 2003 | ICASSP | Combining neighboring filter channels to improve quantile based histogram equalization. | Florian Hilger, Hermann Ney, Olivier Siohan, Frank K. Soong |
| 2003 | ICASSP | Optimal clustering of multivariate normal distributions using divergence and its application to HMM adaptation. | Tor Andr Myrvoll, Frank K. Soong |
| 2003 | Interspeech | Modeling Cantonese pronunciation variation by acoustic model refinement. | Patgi Kam, Tan Lee, Frank K. Soong |
| 2003 | Interspeech | On divergence based clustering of normal distributions and its application to HMM adaptation. | Tor Andr Myrvoll, Frank K. Soong |
| 2002 | ICASSP | A dynamic in-search discriminative training approach for large vocabulary speech recognition. | Hui Jiang, Olivier Siohan, Frank K. Soong, Chin-Hui Lee |
| 2002 | ICASSP | Classifier design for verification of multi-class recognition decision. | Tomoko Matsui, Frank K. Soong, Biing-Hwang Juang |
| 2002 | Interspeech | Bell labs approach to Aurora evaluation on connected digit recognition. | Jingdong Chen, Dimitris Dimitriadis, Hui Jiang, Qi Li, Tor Andr Myrvoll, Olivier Siohan, Frank K. Soong |
| 2002 | Interspeech | Recognition of noisy speech using normalized moments. | Jingdong Chen, Yiteng Huang, Qi Li, Frank K. Soong |
| 2001 | ICASSP | Hierarchical stochastic feature matching for robust speech recognition. | Hui Jiang, Frank K. Soong, Chin-Hui Lee |
| 2001 | Interspeech | Evaluating the Aurora connected digit recognition task - a bell labs approach. | Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran |
| 2001 | Interspeech | A data selection strategy for utterance verification in continuous speech recognition. | Hui Jiang, Frank K. Soong, Chin-Hui Lee |
| 2001 | Interspeech | An auditory system-based feature for robust speech recognition. | Qi Li, Frank K. Soong, Olivier Siohan |
| 2001 | Interspeech | A real-time Japanese broadcast news closed-captioning system. | Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou |
| 2000 | Interspeech | A high-performance auditory feature for robust speech recognition. | Qi Li, Frank K. Soong, Olivier Siohan |
| 2000 | Interspeech | Hands-free human-machine dialogue - corpora, technology and evaluation. | Frank K. Soong, Eric A. Woudenberg |
| 1999 | ICASSP | Hidden Markov models with divergence based vector quantized variances. | Jae H. Kim, Raziel Haimi-Cohen, Frank K. Soong |
| 1999 | ICASSP | A block least squares approach to acoustic echo cancellation. | Eric A. Woudenberg, Frank K. Soong, Biing-Hwang Juang |
| 1998 | Interspeech | Improved utterance rejection using length dependent thresholds. | Sunil K. Gupta, Frank K. Soong |
| 1997 | ICASSP | Generalized mixture of HMMs for continuous speech recognition. | Filipp Korkmazskiy, Biing-Hwang Juang, Frank K. Soong |
| 1996 | ICASSP | High-accuracy connected digit recognition for mobile applications. | Sunil K. Gupta, Frank K. Soong, Raziel Haimi-Cohen |
| 1996 | Interspeech | Quantizing mixture-weights in a tied-mixture HMM. | Sunil K. Gupta, Frank K. Soong, Raziel Haimi-Cohen |
| 1995 | ICASSP | An orthogonal polynomial representation of speech signals and its probabilistic model for text independent speaker verification. | Chi-Shi Liu, Hsiao-Chuan Wang, Frank K. Soong, Chao-Shih Huang |
| 1995 | Interspeech | Large vocabulary, word-based Mandarin dictation system. | Jung-Kuei Chen, Lin-Shan Lee, Frank K. Soong |
| 1995 | Interspeech | Optimizing baseforms for HMM-based speech recognition. | Torbjrn Svendsen, Frank K. Soong, Heiko Purnhagen |
| 1994 | ICASSP | Discriminative training of high performance speech recognizer using N best candidates. | Jung-Kuei Chen, Frank K. Soong |
| 1994 | ICASSP | Large vocabulary word recognition based on tree-trellis search. | Jung-Kuei Chen, Frank K. Soong, Lin-Shan Lee |
| 1994 | Interspeech | Cepstral channel normalization techniques for HMM-based speaker verification. | Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong |
| 1992 | ICASSP | Continuous probabilistic acoustic map for speaker recognition. | Belle L. Tseng, Frank K. Soong, Aaron E. Rosenberg |
| 1992 | Interspeech | The use of cohort normalized scores for speaker verification. | Aaron E. Rosenberg, Joel DeLong, Chin-Hui Lee, Biing-Hwang Juang, Frank K. Soong |
| 1992 | Interspeech | Continuous mixture HMM-LR using the a* algorithm for continuous speech recognition. | Kouichi Yamaguchi, Shigeki Sagayama, Kenji Kita, Frank K. Soong |
| 1991 | ICASSP | A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition. | Frank K. Soong, Eng-Fong Huang |
| 1990 | ICASSP | Statistical segmentation and word modeling techniques in isolated word recognition. | S. A. Euler, Biing-Hwang Juang, Chin-Hui Lee, Frank K. Soong |
| 1990 | ICASSP | A probabilistic acoustic map based discriminative HMM training. | Eng-Fong Huang, Frank K. Soong |
| 1990 | ICASSP | Speaker recognition based on source coding approaches. | Biing-Hwang Juang, Frank K. Soong |
| 1990 | ICASSP | Sub-word unit talker verification using hidden Markov models. | Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong |
| 1990 | ICASSP | Optimal quantization of LSP parameters using delayed decisions. | Frank K. Soong, Biing-Hwang Juang |
| 1990 | Interspeech | Experiments in automatic talker verification using sub-word unit hidden Markov models. | Aaron E. Rosenberg, Chin-Hui Lee, Frank K. Soong, Maureen A. McGee |
| 1990 | Interspeech | A tree-trellis based fast search for finding the n best sentence hypotheses in continuous speech recognition. | Frank K. Soong, Eng-Fong Huang |
| 1990 | NAACL | A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition. | Frank K. Soong, Eng-Fong Huang |
| 1989 | ICASSP | Word recognition using whole word and subword models. | Chin-Hui Lee, Biing-Hwang Juang, Frank K. Soong, Lawrence R. Rabiner |
| 1989 | ICASSP | A phonetically labeled acoustic segment (PLAS) approach to speech analysis-synthesis. | Frank K. Soong |
| 1988 | ICASSP | A segment model based approach to speech recognition. | Chin-Hui Lee, Frank K. Soong, Biing-Hwang Juang |
| 1988 | ICASSP | High performance connected digit recognition, using hidden Markov models. | Lawrence R. Rabiner, Jay G. Wilpon, Frank K. Soong |
| 1988 | ICASSP | Optimal quantization of LSP parameters [speech coding]. | Frank K. Soong, Bling-Hwang Juang |
| 1987 | ICASSP | A training procedure for a segment-based-network approach to isolated word recognition. | Frank K. Soong |
| 1987 | ICASSP | A frequency-weighted Itakura spectral distortion measure and its application to speech recognition in noise. | Frank K. Soong, M. Mohan Sondhi |
| 1987 | ICASSP | On the automatic segmentation of speech signals. | Torbjrn Svendsen, Frank K. Soong |
| 1986 | ICASSP | Evaluation of a vector quantization talker recognition system in text independent and text dependent modes. | Aaron E. Rosenberg, Frank K. Soong |
| 1986 | ICASSP | A high quality subband speech coder with backward adaptive predictor and optimal time-frequency bit assignment. | Frank K. Soong, Richard V. Cox, Nikil S. Jayant |
| 1986 | ICASSP | On the use of instantaneous and transitional spectral information in speaker recognition. | Frank K. Soong, Aaron E. Rosenberg |
| 1985 | ICASSP | Comparative study of several distortion measures for speech recognition. | N. Nocerino, Frank K. Soong, Lawrence R. Rabiner, Dennis H. Klatt |
| 1985 | ICASSP | An efficient vector-quantization preprocessor for speaker independent isolated word recognition. | Kuk-Chin Pan, Frank K. Soong, Lawrence R. Rabiner, A. F. Bergh |
| 1985 | ICASSP | Subband coding of speech using backward adaptive prediction and bit allocation. | Frank K. Soong, Richard V. Cox, Nikil S. Jayant |
| 1985 | ICASSP | A vector quantization approach to speaker recognition. | Frank K. Soong, Aaron E. Rosenberg, Lawrence R. Rabiner, Biing-Hwang Juang |
| 1984 | ICASSP | On the use of transient information in speech recognition. | Jean-Sylvain Linard, Frank K. Soong |
| 1984 | ICASSP | Line spectrum pair (LSP) and speech data compression. | Frank K. Soong, Biing-Hwang Juang |
| 1982 | ICASSP | On the high resolution and unbiased frequency estimates of sinusoids in white noise-A new adaptive approach. | Frank K. Soong, Allen M. Peterson |
| 1982 | ICASSP | Fast least-squares (LS) in the voice echo cancellation application. | Frank K. Soong, Allen M. Peterson |
| 1981 | ICASSP | On the asymptotic behavior of a complex adaptive line enchancer (CALE). | Frank K. Soong, S. Shankar Narayan, Allen M. Peterson |
| 1980 | ICASSP | Fast spectral estimation of speech signal in analytic form. | Frank K. Soong, Allen M. Peterson |
| 1978 | ICASSP | Observations on linear estimation. | Leland B. Jackson, Frank K. Soong |
| 1978 | ICASSP | Frequency estimation by linear prediction. | Leland B. Jackson, Donald W. Tufts, Frank K. Soong, Rahul M. Rao |