# Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios

arXiv: https://arxiv.org/abs/2506.14204 · HTML: https://mlsanity.com/paper/2506.14204/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency](https://mlsanity.com/paper/2003.12710/) (2020)
- [Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset](https://mlsanity.com/paper/2010.11395/) (2020)
- [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)
- [Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability](https://mlsanity.com/paper/2007.15188/) (2020)
- [Cascaded encoders for unifying streaming and non-streaming ASR](https://mlsanity.com/paper/2010.14606/) (2020)
- [MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition](https://mlsanity.com/paper/1910.06522/) (2019)
- [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)
- [Streaming Multi-Talker ASR with Token-Level Serialized Output Training](https://mlsanity.com/paper/2202.00842/) (2022)
- [Continuous Speech Separation with Conformer](https://mlsanity.com/paper/2008.05773/) (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)
- [Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings](https://mlsanity.com/paper/2008.04546/) (2020)
- [High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model](https://mlsanity.com/paper/2003.07482/) (2020)
- [Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization](https://mlsanity.com/paper/2011.00091/) (2020)
- [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)
- [Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts](https://mlsanity.com/paper/2211.06493/) (2022)

## Abstract (arXiv)

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to real-time captioning and summarization requirements. We propose several key improvements: (1) Leveraging Continuous Speech Separation (CSS) single-channel front-end with end-to-end (E2E) systems for highly overlapping scenarios, challenging the conventional wisdom of E2E versus cascaded setups. The CSS framework improves the accuracy of the ASR system by separating overlapped speech from multiple speakers. (2) Implementing dual models -- Conformer Transducer for streaming and Sequence-to-Sequence for offline -- or alternatively, a two-pass model based on cascaded encoders. (3) Exploring segment-based SOT (segSOT) which is better suited for offline scenarios while also enhancing readability of multi-talker transcriptions.