2021年8月30日 - 2021年9月3日

Microsoft at INTERSPEECH 2021

地点： Brno, Czech Republic & Virtual

所有时间都在 CEST (UTC +2)

13:30 – 15:30 Talk session Virtual

Improving Weakly Supervised Sound Event Detection with Self-Supervised Auxiliary Tasks
相关论文与出版物
- Improving Weakly Supervised Sound Event Detection with Self-Supervised Auxiliary Tasks
  
  Soham Deshmukh, Bhiksha Raj, Rita Singh
13:30 – 15:30 Talk session Virtual

Explaining Deep Learning Models for Speech Enhancement
相关论文与出版物
- Explaining deep learning models for speech enhancement
  
  Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr
13:30 – 15:30 Talk session Virtual

Improving RNN-T for Domain Scaling Using Semi-Supervised Training with Neural TTS
相关论文与出版物
- Improving RNN-T for Domain Scaling Using Semi-Supervised Training with Neural TTS
  
  Yan Deng, Rui Zhao, Zhong Meng, Xie Chen, Bing Liu, Jinyu Li, Yifan Gong, Lei He
19:00 – 21:00 Talk session Virtual

Data Augmentation for Spoken Language Understanding via Pretrained Language Models
相关论文与出版物
- Data Augmentation for Spoken Language Understanding via Pretrained Models
  
  Baolin Peng, Chenguang Zhu, Michael Zeng, Jianfeng Gao
19:00 – 21:00 Talk session Virtual

Rapid Speaker Adaptation for Conformer Transducer: Attention and Bias Are All You Need
相关论文与出版物
- Rapid Speaker Adaptation for Conformer Transducer: Attention and Bias are All You Need
  
  Yan Huang, Guoli Ye, Jinyu Li, Yifan Gong
19:00 – 21:00 Talk session Virtual

One-Shot Voice Conversion with Speaker-Agnostic StarGAN
相关论文与出版物
- One-Shot Voice Conversion with Speaker-Agnostic StarGAN
  
  Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr

11:00 – 13:00 Talk session Virtual

Multiple Softmax Architecture for Streaming Multilingual End-to-End ASR Systems
相关论文与出版物
- Multiple Softmax Architecture for Streaming Multilingual End-to-End ASR Systems
  
  Vikas Joshi, Amit Das, Eric Sun, Rupesh Mehta, Jinyu Li, Yifan Gong
11:00 – 13:00 Talk session Virtual

Streaming Multi-Talker Speech Recognition with Joint Speaker Identification
相关论文与出版物
- Streaming Multi-talker Speech Recognition with Joint Speaker Identification
  
  Liang Lu, Naoyuki Kanda, Jinyu Li, Yifan Gong
16:00 – 18:00 Talk session Virtual

A Light-Weight Contextual Spelling Correction Model for Customizing Transducer-Based Speech Recognition Systems
相关论文与出版物
- A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
  
  Xiaoqiang Wang, Yanqing Liu, Sheng Zhao, Jinyu Li
16:00 – 18:00 Talk session Virtual

Subjective Evaluation of Noise Suppression Algorithms in Crowdsourcing
相关论文与出版物
- Subjective Evaluation of Noise Suppression Algorithms in Crowdsourcing
  
  Babak Naderi, Ross Cutler
19:00 – 21:00 Talk session Virtual

MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages
相关论文与出版物
- Multilingual and code-switching ASR challenges for low resource Indian languages
  
  Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah, Ankita Singh, Srinivasa Raghavan, Shreya Khare, Vinit Unni, Saurabh Vyas, Akash Rajpuria, Chiranjeevi Yarra, Ashish Mittal, Prasanta Kumar Ghosh, Preethi Jyothi, Kalika Bali, Vivek Seshadri, Sunayana Sitaram, Samarth Bharadwaj, Jai Nanavati, Raoul Nanavati, Karthik Sankaranarayanan, Tejaswi Seeram, Basil Abraham
19:00 – 21:00 Talk session Virtual

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
相关论文与出版物
- Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
  
  Zhong Meng, Yu Wu, Naoyuki Kanda, Liang Lu, Xie Chen, Guoli Ye, Eric Sun, Jinyu Li, Yifan Gong
19:00 – 21:00 Talk session Virtual

Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
相关论文与出版物
- Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
  
  Sefik Emre Eskimez, Xiaofei Wang, Min Tang, Hemin Yang, Zirun Zhu, Zhuo Chen, Huaming Wang, Takuya Yoshioka
19:00 – 21:00 Talk session Virtual

Single-Channel Speech Enhancement Using Learnable Loss Mixup
相关论文与出版物
- Single-Channel Speech Enhancement Using Learnable Loss Mixup
  
  Oscar Chang, Dung N. Tran, Kazuhito Koishida
19:00 – 21:00 Talk session Virtual

INTERSPEECH 2021 Deep Noise Suppression Challenge
相关论文与出版物
- INTERSPEECH 2021 Deep Noise Suppression Challenge
  
  Chandan K. A. Reddy, Harishchandra Dubey, Kazuhito Koishida, Arun Asokan Nair, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan

11:00 – 13:00 Talk session Virtual

Analyzing Short Term Dynamic Speech Features for Understanding Behavioral Traits of Children with Autism Spectrum Disorder
相关论文与出版物
- Analyzing short term dynamic speech features for understanding behavioral traits of children with autism spectrum disorder
  
  Young-Kyung Kim, Rimita Lahiri, Md Nasir, So Hyun Kim, Somer Bishop, Catherine Lord, Shrikanth Narayanan
11:00 – 13:00 Talk session Virtual

Source Separation I
相关论文与出版物
- Ultra Fast Speech Separation Model with Teacher Student Learning
  
  Sanyuan Chen, Yu Wu, Zhuo Chen, Jian Wu, Takuya Yoshioka, Shujie Liu, Jinyu Li, Xiangzhan Yu
- Investigation of Practical Aspects of Single Channel Speech Separation for ASR
  
  Jian Wu, Zhuo Chen, Sanyuan Chen, Yu Wu, Takuya Yoshioka, Naoyuki Kanda, Shujie Liu, Jinyu Li
- Continuous Speech Separation Using Speaker Inventory for Long Recording
  
  Cong Han, Yi Luo, Chenda Li, Tianyan Zhou, Keisuke Kinoshita, Shinji Watanabe, Marc Delcroix, Hakan Erdogan, John R. Hershey, Nima Mesgarani, Zhuo Chen
16:00 – 18:00 Talk session Virtual

Multi- and cross-lingual ASR, other topics in ASR
相关论文与出版物
- Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching
  
  Wenxin Hou, Jindong Wang, Xu Tan, Tao Qin, Takahiro Shinozaki
- Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
  
  Naoyuki Kanda, Guoli Ye, Yu Wu, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Zhuo Chen, Takuya Yoshioka
- On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
  
  Liang Lu, Zhong Meng, Naoyuki Kanda, Jinyu Li, Yifan Gong
- Improving Multilingual Transformer Transducer Models by Reducing Language Confusions
  
  Eric Sun, Jinyu Li, Zhong Meng, Yu Wu, Jian Xue, Shujie Liu, Yifan Gong
16:00 – 18:00 Talk session Virtual

Target-Speaker Voice Activity Detection with Improved i-Vector Estimation for Unknown Number of Speaker
相关论文与出版物
- Target-Speaker Voice Activity Detection with Improved i-Vector Estimation for Unknown Number of Speaker
  
  Maokui He, Desh Raj, Zili Huang, Jun Du, Zhuo Chen, Shinji Watanabe
16:00 – 18:00 Talk session Virtual

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
相关论文与出版物
- Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
  
  Chuanxin Tang, Chong Luo, Zhiyuan Zhao, Dacheng Yin, Yucheng Zhao, Wenjun Zeng
16:00 – 18:00 Talk session Virtual

AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
相关论文与出版物
- AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
  
  Yihui Fu, Luyao Cheng, Shubo Lv, Yukai Jv, Yuxiang Kong, Zhuo Chen, Yanxin Hu, Lei Xie, Jian Wu, Hui Bu, Xin Xu, Jun Du, Jingdong Chen

11:00 – 13:00 Talk session Virtual

Sequence-Level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
相关论文与出版物
- Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
  
  Amber Afshan, Kshitiz Kumar, Jian Wu
16:00 – 18:00 Talk session Virtual

End-to-End Speaker-Attributed ASR with Transformer
相关论文与出版物
- End-to-End Speaker-Attributed ASR with Transformer
  
  Naoyuki Kanda, Guoli Ye, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Zhuo Chen, Takuya Yoshioka
16:00 – 18:00 Talk session Virtual

Speech Synthesis: Speaking Style and Emotion
相关论文与出版物
- Adaptive Text to Speech for Spontaneous Style
  
  Yuzi Yan, Xu Tan, Bohan Li, Guangyan Zhang, Tao Qin, Sheng Zhao, Yuan Shen, Wei-Qiang Zhang, Tie-Yan Liu
- Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
  
  Shifeng Pan, Lei He
- Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
  
  Xiaochun An, Frank Soong, Lei Xie
16:00 – 18:00 Talk session Virtual

INTERSPEECH 2021 Acoustic Echo Cancellation Challenge
相关论文与出版物
- INTERSPEECH 2021 Acoustic Echo Cancellation Challenge
  
  Ross Cutler, Ando Saabas, Tanel Panarmaa, Markus Loide, Sten Sootla, Marju Purin, Hannes Gamper, Sebastian Braun, Robert Aichner, Sriram Srinivasan

11:00 Workshop

Workshop on Machine Learning in Speech and Language Processing 2021

Speaker: Chengyi Wang (Intern)
Organizing Committee: Yao Qian
Scientific Committee: Liang Lu

Microsoft at INTERSPEECH 2021

Tuesday, August 31, 2021

Improving Weakly Supervised Sound Event Detection with Self-Supervised Auxiliary Tasks

Explaining Deep Learning Models for Speech Enhancement

Improving RNN-T for Domain Scaling Using Semi-Supervised Training with Neural TTS

Data Augmentation for Spoken Language Understanding via Pretrained Language Models

Rapid Speaker Adaptation for Conformer Transducer: Attention and Bias Are All You Need

One-Shot Voice Conversion with Speaker-Agnostic StarGAN

Wednesday, September 1, 2021

Multiple Softmax Architecture for Streaming Multilingual End-to-End ASR Systems

Streaming Multi-Talker Speech Recognition with Joint Speaker Identification

A Light-Weight Contextual Spelling Correction Model for Customizing Transducer-Based Speech Recognition Systems

Subjective Evaluation of Noise Suppression Algorithms in Crowdsourcing

MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages

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

Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement

Single-Channel Speech Enhancement Using Learnable Loss Mixup

INTERSPEECH 2021 Deep Noise Suppression Challenge

Thursday, September 2, 2021

Analyzing Short Term Dynamic Speech Features for Understanding Behavioral Traits of Children with Autism Spectrum Disorder

Source Separation I

Multi- and cross-lingual ASR, other topics in ASR

Target-Speaker Voice Activity Detection with Improved i-Vector Estimation for Unknown Number of Speaker

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario

Friday, September 3, 2021

Sequence-Level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models

End-to-End Speaker-Attributed ASR with Transformer

Speech Synthesis: Speaking Style and Emotion

INTERSPEECH 2021 Acoustic Echo Cancellation Challenge

Monday, September 6, 2021

Workshop on Machine Learning in Speech and Language Processing 2021