2024/09/14 by Alexander Polok, Polok, Alexander, Dominik Klement +9 · 6 citations
Business, Management and Accounting · #Audio and Speech Processing (eess.AS) #Dispute Resolution and Class Actions #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2409.09543
openalex publication_date 2024/09/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose a novel approach to enable the use of large, single-speaker ASR models, such as Whisper, for target speaker ASR. The key claim of this method is that it is much easier to model relative differences among speakers by learning to condition on frame-level diarization outputs than to learn the space of all speaker embeddings. We find that adding even a single bias term per diarization output type before the first transformer block can transform single-speaker ASR models into target-speaker ASR models. Our approach also supports speaker-attributed ASR by sequentially generating transcripts for each speaker in a diarization output. This simplified method outperforms baseline speech separation and diarization cascade by 12.9 % absolute ORC-WER on the NOTSOFAR-1 dataset.