4 papers
Fast and General Automatic Differentiation for Finite-State Methods
Lucas Ondel Yang, Tina Raissi, Martin Kocour +2
We propose a new method, that we coined the ``morphism-trick'', to integrate custom implementations of vector-Jacobian products in automatic differentiation softwares, applicable t…
Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition
Martin Kocour, Martin Karafiat, Alexander Polok +3
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 approa…
Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
Takaaki Hori, Martin Kocour, Adnan Haider +2
This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most comm…
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition
Alexander Polok, Dominik Klement, Martin Kocour +7
Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fai…