End-to-End Multi-Speaker Speech Recognition Using Speaker Embeddings and Transfer Learning

Pavel Denisov, Ngoc Thang Vu


This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from clean speech. This proposed framework does not require any parallel non-overlapped speech materials and is independent of the number of speakers. Our experimental results on overlapped speech datasets show that joint conditioning on speaker embeddings and transfer learning significantly improves the ASR performance.


 DOI: 10.21437/Interspeech.2019-1130

Cite as: Denisov, P., Vu, N.T. (2019) End-to-End Multi-Speaker Speech Recognition Using Speaker Embeddings and Transfer Learning. Proc. Interspeech 2019, 4425-4429, DOI: 10.21437/Interspeech.2019-1130.


@inproceedings{Denisov2019,
  author={Pavel Denisov and Ngoc Thang Vu},
  title={{End-to-End Multi-Speaker Speech Recognition Using Speaker Embeddings and Transfer Learning}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={4425--4429},
  doi={10.21437/Interspeech.2019-1130},
  url={http://dx.doi.org/10.21437/Interspeech.2019-1130}
}