Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder

Abstract

This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a shared speech foundational encoder. We leverage the hidden representations from multiple layers of UME as a residual weighted-sum encoding (RWSE) to effectively use information from different semantic levels, contributing to bottom-up alignment between tasks. This joint training approach captures the inherent interdependencies among the tasks, enhancing overall performance on overlapping speech data. Our evaluations demonstrate that UME substantially improves over the single-task baselines dedicated to SD, SS, and multi-speaker ASR on LibriMix evaluation sets. Notably, for SD, UME outperforms the previous studies, achieving diarization error rates of 1.37% and 2.29% on Libri2Mix and Libri3Mix evaluation sets, respectively.

Accepted to IEEE ASRU 2025

References in corpus (9)

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• Powerset multi-class cross entropy loss for neural speaker diarization
• Encoder-Decoder Based Attractors for End-to-End Neural Diarization
• Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR
• Streaming end-to-end multi-talker speech recognition
• End-to-end training of time domain audio separation and recognition
• TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings
• PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings