Continuous speech separation (CSS) is an approach to handling overlapped speech in conversational audio signals. A real recorded dataset, called LibriCSS, is derived from LibriSpeech by concatenating the corpus utterances to simulate a conversation and capturing the audio replays with far-field microphones.
Source: https://github.com/chenzhuo1011/libri_cssBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
LibriCSS
|
TS-SEP
|
|||
|
LibriCSS
|
Conformer
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
