# Adapting self-supervised models to multi-talker speech recognition using speaker embeddings

arXiv: https://arxiv.org/abs/2211.00482 · HTML: https://mlsanity.com/paper/2211.00482/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2022.

## Built on by (most cited first, 18 of 18)

- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions](https://mlsanity.com/paper/2409.08596/) (2024)
- [Extending Whisper with prompt tuning to target-speaker ASR](https://mlsanity.com/paper/2312.08079/) (2023)
- [One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition](https://mlsanity.com/paper/2310.01688/) (2023)
- [Adapting Multi-Lingual ASR Models for Handling Multiple Talkers](https://mlsanity.com/paper/2305.18747/) (2023)
- [Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System](https://mlsanity.com/paper/2407.09817/) (2024)
- [Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition](https://mlsanity.com/paper/2408.09215/) (2024)
- [Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition](https://mlsanity.com/paper/2409.00815/) (2024)
- [Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition](https://mlsanity.com/paper/2509.04488/) (2025)
- [TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding](https://mlsanity.com/paper/2601.06896/) (2026)
- [TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models](https://mlsanity.com/paper/2505.06660/) (2025)
- [Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio](https://mlsanity.com/paper/2505.10975/) (2025)
- [PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems](https://mlsanity.com/paper/2505.21230/) (2025)
- [SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper](https://mlsanity.com/paper/2601.19194/) (2026)
- [Xiaomi-CocktailASR-1 Technical Report](https://mlsanity.com/paper/2609.11274/) (2026)
- [SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition](https://mlsanity.com/paper/2506.12672/) (2025)
- [CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR](https://mlsanity.com/paper/2601.22792/) (2026)
- [Inference-Time Target Speaker Unlearning in LLM-Based Automatic Speech Recognition](https://mlsanity.com/paper/2609.30439/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have degraded performance for multi-talker scenarios -- possibly due to the domain mismatch -- which severely limits their use for such applications. In this paper, we investigate the adaptation of upstream SSL models to the multi-talker automatic speech recognition (ASR) task under two conditions. First, when segmented utterances are given, we show that adding a target speaker extraction (TSE) module based on enrollment embeddings is complementary to mixture-aware pre-training. Second, for unsegmented mixtures, we propose a novel joint speaker modeling (JSM) approach, which aggregates information from all speakers in the mixture through their embeddings. With controlled experiments on Libri2Mix, we show that using speaker embeddings provides relative WER improvements of 9.1% and 42.1% over strong baselines for the segmented and unsegmented cases, respectively. We also demonstrate the effectiveness of our models for real conversational mixtures through experiments on the AMI dataset.