Naoyuki Kanda

发表

All-Neural Beamformer for Continuous Speech Separation pdf

Naoyuki Kanda, Takuya Yoshioka, Zhuo Chen, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

i-Code: An Integrative and Composable Multimodal Learning Framework

Yujia Xie, Ziyi Yang, Dongdong Chen, 2022, 2205.01818.

i-Code: An Integrative and Composable Multimodal Learning Framework

N. Codella, Xuedong Huang, T. Yoshioka, 2022, AAAI.

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing pdf

Naoyuki Kanda, Furu Wei, Takuya Yoshioka, 2021, ArXiv.

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Jinyu Li, Y. Qian, Furu Wei, 2021, IEEE Journal on Selected Topics in Signal Processing.

Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition

Xie Chen, Jinyu Li, Naoyuki Kanda, 2021, INTERSPEECH.

Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Jinyu Li, T. Yoshioka, Naoyuki Kanda, 2022, INTERSPEECH.

Breaking trade-offs in speech separation with sparsely-gated mixture of experts

T. Yoshioka, Naoyuki Kanda, Zhuo Chen, 2022, ArXiv.

Speech separation with large-scale self-supervised learning

Jinyu Li, T. Yoshioka, Naoyuki Kanda, 2022, ArXiv.

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Jinyu Li, Y. Qian, Furu Wei, 2021, IEEE Journal of Selected Topics in Signal Processing.

LG-001 Management of Query Conditions using Dialogue History in Spoken Dialogue Systems

Naoyuki Kanda, Tetsuya Ogata, Hiroshi G. Okuno, 2004 .

Elastic spectral distortion for low resource speech recognition with deep neural networks

Naoyuki Kanda, Yasunari Obuchi, Ryu Takeda, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

A Review of Speaker Diarization: Recent Advances with Deep Learning

Kyu J. Han, Shrikanth S. Narayanan, Tae Jin Park, 2021, Comput. Speech Lang..

Open-ended Spoken Language Technology: Studies on Spoken Dialogue Systems and Spoken Document Retrieval Systems

Naoyuki Kanda, Naoyuki Kanda, 2014 .

Using rhythmic features for Japanese spoken term detection

Naoyuki Kanda, Yasunari Obuchi, Ryu Takeda, 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

Open-vocabulary keyword detection from super-large scale speech database

Naoyuki Kanda, Yasunari Obuchi, Takashi Sumiyoshi, 2008, 2008 IEEE 10th Workshop on Multimedia Signal Processing.

Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation

Naoyuki Kanda, Xiaofei Wang, Dongmei Wang, 2022, INTERSPEECH.

VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Serialized Output Training for End-to-End Overlapped Speech Recognition pdf

Xiaofei Wang, Naoyuki Kanda, Yashesh Gaur, 2020, INTERSPEECH.

End-to-End Neural Speaker Diarization with Self-Attention

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Microsoft Speaker Diarization System for the Voxceleb Speaker Recognition Challenge 2020 pdf

Naoyuki Kanda, Zhuo Chen, Takuya Yoshioka, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Neural Speaker Diarization with Permutation-Free Objectives

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, INTERSPEECH.

Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization

Naoyuki Kanda, Dongmei Wang, Xiong Xiao, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Factual Consistency Oriented Speech Recognition

Yang Liu, Naoyuki Kanda, Takuya Yoshioka, 2023, INTERSPEECH 2023.

Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone

Naoyuki Kanda, Zhuo Chen, Xiaofei Wang, 2021, Interspeech.

Internal Language Model Training for Domain-Adaptive End-To-End Speech Recognition

Naoyuki Kanda, Yashesh Gaur, Zhong Meng, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech-Language Pre-Training for End-to-End Spoken Language Understanding

Naoyuki Kanda, Zhen Xiao, Michael Zeng, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Streaming Multi-Talker ASR with Token-Level Serialized Output Training

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2022, INTERSPEECH.

Simulating realistic speech overlaps improves multi-talker ASR

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2022, IEEE International Conference on Acoustics, Speech, and Signal Processing.

A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio pdf

Xiong Xiao, Naoyuki Kanda, Yashesh Gaur, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Investigation of Practical Aspects of Single Channel Speech Separation for ASR pdf

Naoyuki Kanda, Takuya Yoshioka, Jinyu Li, 2021, Interspeech.

End-to-End Speaker-Attributed ASR with Transformer pdf

Naoyuki Kanda, Yashesh Gaur, Zhong Meng, 2021, Interspeech.

Streaming Multi-talker Speech Recognition with Joint Speaker Identification pdf

Naoyuki Kanda, Yifan Gong, Jinyu Li, 2021, Interspeech.

Streaming End-to-End Multi-Talker Speech Recognition

Jinyu Li, Y. Gong, Naoyuki Kanda, 2020, IEEE Signal Processing Letters.

Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis pdf

Naoyuki Kanda, Zhuo Chen, Takuya Yoshioka, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers

Naoyuki Kanda, Zhuo Chen, Xiaofei Wang, 2020, INTERSPEECH.

Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR pdf

Naoyuki Kanda, Reinhold Häb-Umbach, Shota Horiguchi, 2019, INTERSPEECH.

Speech separation with large-scale self-supervised learning

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition pdf

Naoyuki Kanda, Yashesh Gaur, Zhong Meng, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition

Naoyuki Kanda, Shinji Watanabe, Ryoichi Takashima, 2019, INTERSPEECH.

Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers Using End-to-End Speaker-Attributed ASR pdf

Naoyuki Kanda, Yashesh Gaur, Takuya Yoshioka, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Investigation of End-to-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings

Xiaofei Wang, Naoyuki Kanda, Yashesh Gaur, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Hypothesis Stitcher for End-to-End Speaker-Attributed ASR on Long-Form Multi-Talker Recordings pdf

Xiaofei Wang, Naoyuki Kanda, Yashesh Gaur, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sequence Distillation for Purely Sequence Trained Acoustic Models

Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

Ziyi Yang, Chenguang Zhu, Dongdong Chen, 2023, ArXiv.

Minimum Bayes risk training of CTC acoustic models in maximum a posteriori based decoding framework

Naoyuki Kanda, Hisashi Kawai, Xugang Lu, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Face-Voice Matching using Cross-modal Embeddings

Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, 2018, ACM Multimedia.

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition pdf

Naoyuki Kanda, Zhong Meng, Yifan Gong, 2021, Interspeech.

On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer pdf

Naoyuki Kanda, Zhong Meng, Yifan Gong, 2020, Interspeech.

Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition

Xie Chen, Jinyu Li, Naoyuki Kanda, 2021, INTERSPEECH.

Adapting Multi-Lingual ASR Models for Handling Multiple Talkers

Y. Qian, Naoyuki Kanda, Zhuo Chen, 2023, ArXiv.

Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts

Naoyuki Kanda, Zhuo Chen, Xiaofei Wang, 2022, 2211.06493.

Maximum-a-Posteriori-Based Decoding for End-to-End Acoustic Models

Naoyuki Kanda, Hisashi Kawai, Xugang Lu, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

SpeechX: Neural Codec Language Model as a Versatile Speech Transformer

Jinyu Li, Naoyuki Kanda, Zhuo Chen, 2023, ArXiv.

Maximum a posteriori Based Decoding for CTC Acoustic Models

Naoyuki Kanda, Hisashi Kawai, Xugang Lu, 2016, INTERSPEECH.

A multi-expert model for dialogue and behavior control of conversational robots and agents

Naoyuki Kanda, Hiroshi G. Okuno, Mikio Nakano, 2011, Knowl. Based Syst..

Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors

Naoyuki Kanda, Tetsuya Ogata, Hiroshi G. Okuno, 2006, SIGDIAL Workshop.

Target Speaker Voice Activity Detection with Transformers and Its Integration with End-To-End Neural Diarization

Naoyuki Kanda, Dongmei Wang, Xiong Xiao, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Investigation of lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence

Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

VarArray: Array-Geometry-Agnostic Continuous Speech Separation pdf

Naoyuki Kanda, Takuya Yoshioka, Zhuo Chen, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription

Naoyuki Kanda, Eyal Krupka, S. Koubi, 2024, ArXiv.

Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Diarist: Streaming Speech Translation with Speaker Diarization

Naoyuki Kanda, Xiaofei Wang, Muqiao Yang, 2023, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Training data pseudo-shuffling and direct decoding framework for recurrent neural network based acoustic modeling

Naoyuki Kanda, Hisashi Kawai, Xugang Lu, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).