# SURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition

arXiv: https://arxiv.org/abs/2306.10559 · HTML: https://mlsanity.com/paper/2306.10559/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2023.

## Built on by (most cited first, 8 of 8)

- [Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions](https://mlsanity.com/paper/2409.08596/) (2024)
- [Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System](https://mlsanity.com/paper/2407.09817/) (2024)
- [Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC](https://mlsanity.com/paper/2409.12388/) (2024)
- [Alignment-Free Training for Transducer-based Multi-Talker ASR](https://mlsanity.com/paper/2409.20301/) (2024)
- [Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition](https://mlsanity.com/paper/2510.03723/) (2025)
- [CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models](https://mlsanity.com/paper/2506.12059/) (2025)
- [SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition](https://mlsanity.com/paper/2506.12672/) (2025)
- [G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition](https://mlsanity.com/paper/2603.10468/) (2026)

## Abstract (arXiv)

The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR). Despite impressive results on multi-turn meetings, SURT has notable limitations: (i) it suffers from leakage and omission related errors; (ii) it is computationally expensive, due to which it has not seen adoption in academia; and (iii) it has only been evaluated on synthetic mixtures. In this work, we propose several modifications to the original SURT which are carefully designed to fix the above limitations. In particular, we (i) change the unmixing module to a mask estimator that uses dual-path modeling, (ii) use a streaming zipformer encoder and a stateless decoder for the transducer, (iii) perform mixture simulation using force-aligned subsegments, (iv) pre-train the transducer on single-speaker data, (v) use auxiliary objectives in the form of masking loss and encoder CTC loss, and (vi) perform domain adaptation for far-field recognition. We show that our modifications allow SURT 2.0 to outperform its predecessor in terms of multi-talker ASR results, while being efficient enough to train with academic resources. We conduct our evaluations on 3 publicly available meeting benchmarks -- LibriCSS, AMI, and ICSI, where our best model achieves WERs of 16.9%, 44.6% and 32.2%, respectively, on far-field unsegmented recordings. We release training recipes and pre-trained models: https://sites.google.com/view/surt2.