Error Analysis in a Modular Meeting Transcription System
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909783742742528 |
|---|---|
| author | Vieting, Peter Berger, Simon von Neumann, Thilo Boeddeker, Christoph Schlüter, Ralf Haeb-Umbach, Reinhold |
| author_facet | Vieting, Peter Berger, Simon von Neumann, Thilo Boeddeker, Christoph Schlüter, Ralf Haeb-Umbach, Reinhold |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10143 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Error Analysis in a Modular Meeting Transcription System Vieting, Peter Berger, Simon von Neumann, Thilo Boeddeker, Christoph Schlüter, Ralf Haeb-Umbach, Reinhold Audio and Speech Processing Computation and Language Machine Learning Sound 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. |
| title | Error Analysis in a Modular Meeting Transcription System |
| topic | Audio and Speech Processing Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2509.10143 |