# Error Analysis in a Modular Meeting Transcription System

arXiv: https://arxiv.org/abs/2509.10143 · HTML: https://mlsanity.com/paper/2509.10143/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [Language Modeling with Deep Transformers](https://mlsanity.com/paper/1905.04226/) (2019)
- [Continuous speech separation: dataset and analysis](https://mlsanity.com/paper/2001.11482/) (2020)
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation](https://mlsanity.com/paper/2209.03952/) (2022)
- [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)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems](https://mlsanity.com/paper/2307.11394/) (2023)
- [Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks](https://mlsanity.com/paper/1810.03655/) (2018)
- [SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition](https://mlsanity.com/paper/1910.13934/) (2019)
- [TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings](https://mlsanity.com/paper/2303.03849/) (2023)
- [Multi-turn RNN-T for streaming recognition of multi-party speech](https://mlsanity.com/paper/2112.10200/) (2021)
- [Monaural source separation: From anechoic to reverberant environments](https://mlsanity.com/paper/2111.07578/) (2021)
- [Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization](https://mlsanity.com/paper/2309.16482/) (2023)
- [Mixture Encoder for Joint Speech Separation and Recognition](https://mlsanity.com/paper/2306.12173/) (2023)
- [DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions](https://mlsanity.com/paper/2411.06667/) (2024)
- [Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment](https://mlsanity.com/paper/2406.03155/) (2024)
- [Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription](https://mlsanity.com/paper/2309.08454/) (2023)

## Built on by (most cited first, 1 of 1)

- [Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction](https://mlsanity.com/paper/2608.22196/) (2026)

## Abstract (arXiv)

Meeting transcription is a field of high relevance and remarkable progress in recent years. Still, challenges remain that limit its performance. In this work, we extend a previously proposed framework for analyzing leakage in speech separation with proper sensitivity to temporal locality. We show that there is significant leakage to the cross channel in areas where only the primary speaker is active. At the same time, the results demonstrate that this does not affect the final performance much as these leaked parts are largely ignored by the voice activity detection (VAD). Furthermore, different segmentations are compared showing that advanced diarization approaches are able to reduce the gap to oracle segmentation by a third compared to a simple energy-based VAD. We additionally reveal what factors contribute to the remaining difference. The results represent state-of-the-art performance on LibriCSS among systems that train the recognition module on LibriSpeech data only.