ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain

Pengcheng Guo, Xuankai Chang, Shinji Watanabe, Lei Xie

Non-autoregressive (NAR) models have achieved a large inference computation reduction and comparable results with autoregressive (AR) models on various sequence to sequence tasks. However, there has been limited research aiming to explore the NAR approaches on sequence to multi-sequence problems, like multi-speaker automatic speech recognition (ASR). In this study, we extend our proposed conditional chain model to NAR multi-speaker ASR. Specifically, the output of each speaker is inferred one-by-one using both the input mixture speech and previously-estimated conditional speaker features. In each step, a NAR connectionist temporal classification (CTC) encoder is used to perform parallel computation. With this design, the total inference steps will be restricted to the number of mixed speakers. Besides, we also adopt the Conformer and incorporate an intermediate CTC loss to improve the performance. Experiments on WSJ0-Mix and LibriMix corpora show that our model outperforms other NAR models with only a slight increase of latency, achieving WERs of 22.3% and 24.9%, respectively. Moreover, by including the data of variable numbers of speakers, our model can even better than the PIT-Conformer AR model with only 1/7 latency, obtaining WERs of 19.9% and 34.3% on WSJ0-2mix and WSJ0-3mix sets. All of our codes are publicly available.


doi: 10.21437/Interspeech.2021-2155

Cite as: Guo, P., Chang, X., Watanabe, S., Xie, L. (2021) Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain. Proc. Interspeech 2021, 3720-3724, doi: 10.21437/Interspeech.2021-2155

@inproceedings{guo21_interspeech,
  author={Pengcheng Guo and Xuankai Chang and Shinji Watanabe and Lei Xie},
  title={{Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={3720--3724},
  doi={10.21437/Interspeech.2021-2155}
}