Paper Info
Title
Exploring End-To-End Multi-Channel Asr With Bias Information For Meeting Transcription
Abstract
Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were limited to small scale experiments. It is still unclear whether such a joint framework can be beneficial for a more practical setup where a massive amount of single channel training data can be leveraged for building a strong ASR backend. In this work, we present our investigation on the joint modeling of a mask-based beamformer and Attention-Encoder-Decoder-based ASR in the setting where we have 75k hours of single-channel data and a relatively small amount of real multi-channel data for model training. We explore effective training procedures, including a comparison of simulated and real multi-channel training data. To guide the recognition towards a target speaker and deal with overlapped speech, we also explore various combinations of bias information, such as direction of arrivals and speaker profiles. We propose an effective location bias integration method called deep concatenation for the beamformer network. In our evaluation on various meeting recordings, we show that the proposed framework achieves a substantial word error rate reduction.
Year
DOI
Venue
2021
10.1109/SLT48900.2021.9383500
2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT)
Keywords
DocType
ISSN
Meeting transcription, end-to-end multi-channel ASR, target-speaker ASR, bias information
Conference
2639-5479
Citations 
PageRank 
References 
0
0.34
0
Authors
6
Name
Order
Citations
PageRank
Xiaofei Wang100.34
Naoyuki Kanda210319.45
Yashesh Gaur3159.06
Zhuo Chen415324.33
Zhong Meng53314.95
Takuya Yoshioka658549.20