Publications

Journals (Peer reviewed)

• Coupling a generative model with a discriminative learning framework for speaker verification
  X. Lu, P. Shen, Y. Tsao, H. Kawai
  In IEEE/ACM Trans. on Audio, Speech and Language Processing, vol. 29, 2021.
  
• Knowledge distillation-based representation learning for short-utterance spoken language identification
  Peng Shen, Xugang Lu, Sheng Li, Hisashi Kawai
  In IEEE/ACM Trans. on Audio, Speech and Language Processing, vol. 28, pp. 2674-2683, 2020.
  
• Regularization of neural network model with distance metric learning for i-vector based spoken language identification
  Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai
  In Computer Speech and Language, vol. 44, pp. 48–60, July 2017.
  
• Combination of multiple acoustic models with unsupervised adaptation for lecture speech transcription
  Peng Shen, Xugang Lu, Xinhui Hu, Naoyuki Kanda, Masahiro Saiko, Chiori Hori, Hisashi Kawai
  In Speech Communication, vol.82, pp. 1-13, Sep, 2016.
  
• Multi-Stream Sparse Representation Features for Noise Robust Audio-Visual Speech Recognition
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In journal of Acoustical Science and Technology, vol.35, no.1, 2014.
  

International Conferences (Peer reviewed)

• Generative linguistic representation for spoken language identification
  P. Shen, X. Lu, H. Kawai
  in Proc. ASRU, 2023. (Accepted)
  
• Cross-modal alignment with optimal transport for CTC-based ASR
  X. Lu, P. Shen, Y. Tsao, H. Kawai
  in Proc. ASRU, 2023. (Accepted)
  
• Unsupervised neural adaptation model based on optimal transport for spoken language identification
  X. Lu, P. Shen, Y. Tsao, H. Kawai
  in Proc. ICASSP, 2022.
  
• Pronunciation-aware unique character encoding for RNN Transducer-based Mandarin speech recognition
  P. Shen, X. Lu, H. Kawai
  in Proc. SLT, 2022.
  
• Transducer-based language embedding for spoken language identification
  P. Shen, X. Lu, H. Kawai
  in Proc. Interspeech, 2022.
  
• Siamese Neural Network with Joint Bayesian Model Structure for Speaker Verification
  X. Lu, P. Shen, Y. Tsao, H. Kawai
  in Proc. APSIPA ASC, 2021.
  
• Unsupervised neural adaptation model based on optimal transport for spoken language identification
  X. Lu, P. Shen, Y. Tsao, H. Kawai
  in Proc. ICASSP, 2021.
  
• Investigation of NICT submission for short-duration speaker verification challenge 2020
  Peng Shen, Xugang Lu, and Hisashi Kawai
  in Proc. of Interspeech, 2020.
  
• Joint Training End-to-End Speech Recognition Systems with Speaker Attributes
  S. Li, X. Lu, R. Dabre, P. Shen and H. Kawai
  in Proc. ISCA-Odyssey (The Speaker and Language Recognition Workshop), 2020.
  
• Compensation on x-vector for short utterance spoken language identification
  Peng Shen, Xugang Lu, Komei Sugiura, Sheng Li and Hisashi Kawai
  in Proc. ISCA-Odyssey (The Speaker and Language Recognition Workshop), 2020.
  
• Class-wise Centroid Distance Metric Learning for Acoustic Event Detection
  Xugang Lu, Peng Shen, Sheng Li, Yu Tsao and Hisashi Kawai
  in Proc. of Interspeech, 2019.
  
• Investigating Radical-based End-to-End Speech Recognition Systems for Chinese Dialects and Japanese
  Sheng Li, Xugang Lu, Chenchen Ding, Peng Shen, Tatsuya Kawahara and Hisashi Kawai
  in Proc. of Interspeech, 2019.
  
• End-to-End Articulatory Attribute Modeling for Low-resource Multilingual Speech Recognition
  Sheng Li, Chenchen Ding, Xugang Lu, Peng Shen, Tatsuya Kawahara and Hisashi Kawai
  in Proc. of Interspeech, 2019.
  
• Improving Transformer-based Speech Recognition Systems with Compressed Structure and Speech Attributes Augmentation
  Sheng Li, Raj Dabre, Xugang Lu, Peng Shen, Tatsuya Kawahara and Hisashi Kawai
  in Proc. of Interspeech, 2019.
  
• Interactive learning of teacher-student model for short utterance spoken language identification
  Peng Shen, Xugang Lu, Sheng Li and Hisashi Kawai
  In Proc. of ICASSP, May 2019.
  
• Improving very deep time-delay neural network with vertical-attention for effectively training CTC-based ASR systems
  Sheng Li, Xugang Lu, Ryoichi Takashima, Peng Shen, Tatsuya Kawahara and Hisashi Kawai
  In Proc. of SLT, Athens, Greece, 18-21, Dec. 2018.
• Feature Representation of Short Utterances based on Knowledge Distillation for Spoken Language Identification
  Peng Shen, Xugang Lu, Sheng Li and Hisashi Kawai
  In Proc. of Interspeech2018, India, 2-6, Sep. 2018.
  
• Temporal attentive pooling for acoustic event detection
  Xugang Lu, Peng Shen, Sheng Li, Yu Tsao and Hisashi Kawai
  in Proc. of Interspeech2018, India, 2-6, Sep. 2018.
  
• Improving CTC-based Acoustic Model with Very Deep Residual Time-delay Neural Networks
  Sheng Li, Xugang Lu, Ryoichi Takashima, Peng Shen, Tatsuya Kawahara and Hisashi Kawai
  In Proc. of Interspeech, India, 2-6, Sep. 2018.
  
• Incremental training and construction the very deep convolutional residual network acoustic models
  Sheng Li, Xugang Lu, Peng Shen, Ryoichi Takashima, Tatsuya Kawahara and Hisashi Kawai
  In Proc. of ASRU, Okinawa, Japan, 16-20, Dec. 2017.
  
• Conditional Generative Adversarial Nets Classifier for Spoken Language Identification
  Peng Shen, Xugang Lu, Sheng Li, Hisashi Kawai
  In Proc. of Interspeech, Stochholm, Sweden, Aug. 20-24, 2017.
  
• Comparison of Regularization Constraints in Deep Neural Network based Speaker Adaptation
  Peng Shen, Xugang Lu, Hisashi Kawai
  In The 10th International Symposium on Chinese Spoken Language Processing, Oct. 2016.
  
• "Automatic acoustic segmentation in N-best list rescoring for lecture speech recognition"
  Peng Shen, Xugang Lu, Hisashi Kawai,
  in The 9th International Symposium on Chinese Spoken Language Processing, Oct. 2016.
  
• A Pseudo-task Design in Multi-task Learning Deep Neural Network for Speaker Recognition
  Xugang Lu, Peng Shen, Hisashi Kawai
  In The 9th International Symposium on Chinese Spoken Language Processing, Oct. 2016.
  
• Pair-wise Distance Metric Learning of Neural Network Model for Spoken Language Identification
  Xugang Lu, Peng Shen, Yu Tsao, and Hisashi Kawai
  In Proc. Interspeech, Sep. 2016.
  
• Local fisher discriminant analysis for spoken language identification
  Peng Shen, Xugang Lu, Lemao Liu and Hisashi Kawai
  In Proc. ICASSP, Mar. 2016.
  
• Sparse representation with temporal max-smoothing for acoustic event detection
  Xugang Lu, Peng Shen, Yu Tsao, Chiori Hori and Hisashi Kawai
  In Proc. Interspeech, pp. 1176-1180, Sep. 2015.
  
• The NICT ASR System for IWSLT 2014
  Peng Shen, Xugang Lu, Xinhui Hu, Naoyuki Kanda, Masahiro Saiko, Chiori Hori
  In International Workshop on Spoken Language Translation (IWSLT), Lake Tahoe, USA, pp.113-118, Dec. 2014.
  
• Spectral Patch Based Sparse Coding for Acoustic Event Detection
  Xugang Lu, Yu Tsao, Peng Shen, Chiori Hori
  In The 9th International Symposium on Chinese Spoken Language Processing (ISCSLP), Singapore, Set. 2014.
  
• Audio-visual Interaction in Sparse Representation Features for Noise Robust Audio-visual Speech Recognition
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In The 12th International Conference on Auditory-Visual Speech Processing(AVSP), Annecy, France, pp.43-48, Aug. 2013.
  
• Feature Reconstruction using Sparse Imputation for Noise Robust Audio-Visual Speech Recognition
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In Int. Conf. APSIPA ASC, USA, ps.5-sla.18, no.125, pp.1-4, Dec, 2012.
  
• Evaluation of real-time audio-visual speech recognition
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In The 9th International Conference on Auditory-Visual Speech Processing (AVSP), Hakone, Japan, pp.77-80, Oct. 2010.
  

Domestic Conferences

• Investigation on Multi-task Universal Speech Models
  P. Shen, X. Lu, H. Kawai
  in Autumn Meeting of Acoustical Society of Japan, 2023.
  
• Investigation on sub-character tokenization for RNN-Transducer
  P. Shen, X. Lu, H. Kawai
  in Autumn Meeting of Acoustical Society of Japan, 2022.
  
• A Study on Language Modeling with BERT-based Word Embedding
  T. Ogura, M. Fujimoto, P. Shen, X. Lu, H. Kawai
  in Acoustical Society of Japan, Sep, 2021. [In Japanese]
  
• Unsupervised Feature Learning based on wav2vec for Cross-channel Spoken Language Identification
  T. Yoshimoto, P. Shen, X. Lu, R. Takashima, T. Takiguchi, H. Kawai
  in Acoustical Society of Japan, spring, 2021. [In Japanese]
  
• Improvement of x-vector for short utterance spoken language identification
  P. Shen, X. Lu, K. Sugiura, S. Li, H. Kawai
  in Acoustical Society of Japan, spring, 2020.
  
• End-to-End Articulatory Attribute Modeling for Low-resource Multilingual Speech Recognition
  S. Li, C. Ding, X. Lu, P. Shen and H. Kawai
  in Acoustical Society of Japan, spring, 2020.
  
• Joint Training End-to-End Systems for Speech and Speaker Recognition with Speaker Attributes
  S. Li, X. Lu, R. Dabre, P. Shen and H. Kawai
  in Acoustical Society of Japan, spring, 2020.
  
• Investigation of multi-domain training for speech recognition
  Peng Shen, Xugang Lu, Sheng Li and Hisashi Kawai
  in 2019 Acoustical Society of Japan, Mar. 2019.
  
• Short utterance-based spoken language identification
  Peng Shen, Xugang Lu, Sheng Li and Hisashi Kawai
  in 2018 Acoustical Society of Japan, Set. 2018.
  
• An empirical comparison of sequence training methods for the very deep residual time-delay neural network
  Sheng Li, Xugang Lu, Ryoichi Takashima, Peng Shen and Hisashi Kawai
  in 2018 Acoustical Society of Japan, Sep. 2018.
  
• Improving CTC-based acoustic model with very deep residual neural network
  S. Li, X. Lu, R.Takashima, P. Shen and H. Kawai
  In Acoustical Society of Japan, spring, 2018.
  
• cGAN-classifier: Conditional Generative Adversarial Nets for Classification
  Peng Shen, Xugang Lu, Sheng Li and Hisashi Kawai
  In Acoustical Society of Japan, Set. 2017.
  
• Very deep convolutional residual network acoustic models for Japanese lecture transcription
  Sheng Li, Xugang Lu, Peng Shen and Hisashi Kawai
  In Acoustical Society of Japan, Set. 2017.
  
• Building WFST based Grapheme to Phoneme Conversion for Khmer
  Kak Soky, Xugang Lu, Peng Shen, Hiroaki Kato, Hisashi Kawai, Chuon Vanna, Vichet Chea
  In KNLP, 2016.
  
• Investigation on nonparametric discriminant analysis for language identification
  Peng Shen, Xugang Lu and Hisashi Kawai
  In 2016 Spring Meeting of Acoustical Society of Japan, Mar. 2016.
  
• The 2014 NICT Automatic Speech Recognition System
  Peng Shen, Xugang Lu, Xinhui Hu, Naoyuki Kanda, Masahiro Saiko, Chiori Hori
  In 2015 Spring Meeting of Acoustical Society of Japan, 1-P-20, March, 2015.
  
• Feature Reconstruction using Sparse Imputation for Noise Robust Audio-Visual Speech Recognition
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In 2012 Autumn Meeting Acoustical Society of Japan, 3-P-8, pp.217-218, Set. 2012. (In Japanese)
  
• Recent efforts for high-performance multimodal speech recognition
  Satoshi Tamura, Peng Shen, Hiroya Okuda, Naoya Ukai, Takuya Kawasaki, Takumi Seko, Satoru Hayamizu
  In Technical Reports. Information Processing Society of Japan, vol.112, no.369, pp.41-46, Dec. 2012. (in Japanese)
  
• Development of Real-time Audio-Visual Speech Recognition System
  Peng Shen, Satoshi Tamura and Satoru Hayamizu
  In 2010 Spring Meeting of Acoustical Society of Japan, 1-P-27, pp.217-218, March, 2010.