Year: 2020
Type: preprint
Abstract: We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
Source: arXiv (Cornell University)
Authors: Nachmani, Eliya, Adi, Yossi, Wolf, Lior
Institutions: Tel Aviv University, Bar-Ilan University
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Tel Aviv University
OpenAlex ID: W3009168039
