End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning
Audio and Speech Processing
2019-08-14 v1 Computation and Language
Machine Learning
Sound
Abstract
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.
Cite
@article{arxiv.1908.04737,
title = {End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning},
author = {Pavel Denisov and Ngoc Thang Vu},
journal= {arXiv preprint arXiv:1908.04737},
year = {2019}
}
Comments
Interspeech 2019