Conversational Speech Separation: an Evaluation Study for Streaming Applications

Morrone G, Cornell S, Zovato E, Brutti A, Squartini S. Conversational Speech Separation: an Evaluation Study for Streaming Applications. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10562. Available from: https://aes.org/publications/elibrary-page/?id=21675

@inproceedings{Morrone2022_21675,
  author = {Morrone, Giovanni and Cornell, Samuele and Zovato, Enrico and Brutti, Alessio and Squartini, Stefano},
  title = {{Conversational Speech Separation: an Evaluation Study for Streaming Applications}},
  booktitle = {AES Convention 152},
  note = {Paper 10562},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21675}
}

TY  - CPAPER
TI  - Conversational Speech Separation: an Evaluation Study for Streaming Applications
AU  - Morrone, Giovanni
AU  - Cornell, Samuele
AU  - Zovato, Enrico
AU  - Brutti, Alessio
AU  - Squartini, Stefano
T2  - AES Convention 152
M1  - Paper 10562
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21675
PB  - Audio Engineering Society
LA  - en
AB  - Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform an evaluation study on practical design considerations for a CSS system, addressing important aspects which have been neglected in recent works. In particular, we focus on the trade-off between separation performance, computational requirements and output latency showing how an offline separation algorithm can be used to perform CSS with a desired latency. We carry out an extensive analysis on the choice of CSS processing window size and hop size on sparsely overlapped data. We find out that the best trade-off between computational burden and performance is obtained for a window of 5 s.
ER  -