Score: 0

Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition

Published: October 4, 2025 | arXiv ID: 2510.03723v1

By: Martin Kocour , Martin Karafiat , Alexander Polok and more

Potential Business Impact:

Lets computers write down who said what.

Business Areas:
Speech Recognition Data and Analytics, Software

We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW) encoder to extract target-speaker embeddings, which are concatenated into a single representation and passed to a shared decoder. This enables the model to transcribe overlapping speech as a serialized output stream with speaker tags and timestamps. In contrast to target-speaker ASR systems such as DiCoW, which decode each speaker separately, our approach performs joint decoding, allowing the decoder to condition on the context of all speakers simultaneously. Experiments show that the model outperforms existing SOT-based approaches and surpasses DiCoW on multi-talker mixtures (e.g., LibriMix).

Page Count
5 pages

Category
Electrical Engineering and Systems Science:
Audio and Speech Processing