Challenges of Multi-Speaker Extraction for Real Conversational Speech Enhancement

Excerpt

arXiv:2609.25948v1 Announce Type: cross Abstract: Target-speaker and multi-speaker extraction are techniques for extracting speech from a desired speaker or desired speakers in the presence of other speakers and/or noise. Neural network approaches for this task are often trained and evaluated using simulated datasets, with balanced amounts of target speech and speaker enrolment samples which closely match the target speech. However, in real multi-party conversations, participants are often silen