# Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone

arXiv: https://arxiv.org/abs/2103.16776 · HTML: https://mlsanity.com/paper/2103.16776/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Serialized Output Training for End-to-End Overlapped Speech Recognition](https://mlsanity.com/paper/2003.12687/) (2020)
- [Continuous speech separation: dataset and analysis](https://mlsanity.com/paper/2001.11482/) (2020)
- [End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results](https://mlsanity.com/paper/1412.1602/) (2014)
- [End-to-End Multi-speaker Speech Recognition with Transformer](https://mlsanity.com/paper/2002.03921/) (2020)
- [Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers](https://mlsanity.com/paper/2006.10930/) (2020)
- [Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis](https://mlsanity.com/paper/2011.02014/) (2020)
- [Recognizing Multi-talker Speech with Permutation Invariant Training](https://mlsanity.com/paper/1704.01985/) (2017)
- [Streaming end-to-end multi-talker speech recognition](https://mlsanity.com/paper/2011.13148/) (2020)
- [Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings](https://mlsanity.com/paper/2008.04546/) (2020)
- [End-to-End Monaural Multi-speaker ASR System without Pretraining](https://mlsanity.com/paper/1811.02062/) (2018)
- [Advances in Online Audio-Visual Meeting Transcription](https://mlsanity.com/paper/1912.04979/) (2019)
- [Streaming Multi-speaker ASR with RNN-T](https://mlsanity.com/paper/2011.11671/) (2020)
- [Transfer Learning Approaches for Streaming End-to-End Speech Recognition System](https://mlsanity.com/paper/2008.05086/) (2020)
- [Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings](https://mlsanity.com/paper/2101.01853/) (2021)

## Built on by (most cited first, 30 of 33)

- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Streaming Multi-Talker ASR with Token-Level Serialized Output Training](https://mlsanity.com/paper/2202.00842/) (2022)
- [Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR](https://mlsanity.com/paper/2110.03151/) (2021)
- [Adapting Multi-Lingual ASR Models for Handling Multiple Talkers](https://mlsanity.com/paper/2305.18747/) (2023)
- [A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio](https://mlsanity.com/paper/2107.02852/) (2021)
- [Multi-turn RNN-T for streaming recognition of multi-party speech](https://mlsanity.com/paper/2112.10200/) (2021)
- [Simulating realistic speech overlaps improves multi-talker ASR](https://mlsanity.com/paper/2210.15715/) (2022)
- [Advancing Multi-talker ASR Performance with Large Language Models](https://mlsanity.com/paper/2408.17431/) (2024)
- [Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition](https://mlsanity.com/paper/2408.09215/) (2024)
- [VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition](https://mlsanity.com/paper/2209.04974/) (2022)
- [Speech separation with large-scale self-supervised learning](https://mlsanity.com/paper/2211.05172/) (2022)
- [DiariST: Streaming Speech Translation with Speaker Diarization](https://mlsanity.com/paper/2309.08007/) (2023)
- [Serialized Output Training by Learned Dominance](https://mlsanity.com/paper/2407.03966/) (2024)
- [TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding](https://mlsanity.com/paper/2601.06896/) (2026)
- [LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization](https://mlsanity.com/paper/2409.00819/) (2024)
- [Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio](https://mlsanity.com/paper/2505.10975/) (2025)
- [Are E2E ASR models ready for an industrial usage?](https://mlsanity.com/paper/2112.12572/) (2021)
- [The RoyalFlush System of Speech Recognition for M2MeT Challenge](https://mlsanity.com/paper/2202.01614/) (2022)
- [Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech](https://mlsanity.com/paper/2205.05199/) (2022)
- [Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts](https://mlsanity.com/paper/2211.06493/) (2022)
- [End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis](https://mlsanity.com/paper/2310.10106/) (2023)
- [Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications](https://mlsanity.com/paper/2403.06570/) (2024)
- [Using Kaldi for Automatic Speech Recognition of Conversational Austrian German](https://mlsanity.com/paper/2301.06475/) (2023)
- [Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition](https://mlsanity.com/paper/2510.03723/) (2025)
- [SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper](https://mlsanity.com/paper/2601.19194/) (2026)
- [Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2112.12522/) (2021)
- [Enhancing Speech Recognition Decoding via Layer Aggregation](https://mlsanity.com/paper/2203.11325/) (2022)
- [Factual Consistency Oriented Speech Recognition](https://mlsanity.com/paper/2302.12369/) (2023)

## Abstract (arXiv)

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous studies on the monaural overlapped speech recognition problem were based on either simulation data or small-scale real data. In this paper, we extensively investigate a two-step approach where we first pre-train a serialized output training (SOT)-based multi-talker ASR by using large-scale simulation data and then fine-tune the model with a small amount of real meeting data. Experiments are conducted by utilizing 75 thousand (K) hours of our internal single-talker recording to simulate a total of 900K hours of multi-talker audio segments for supervised pre-training. With fine-tuning on the 70 hours of the AMI-SDM training data, our SOT ASR model achieves a word error rate (WER) of 21.2% for the AMI-SDM evaluation set while automatically counting speakers in each test segment. This result is not only significantly better than the previous state-of-the-art WER of 36.4% with oracle utterance boundary information but also better than a result by a similarly fine-tuned single-talker ASR model applied to beamformed audio.