Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
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_ | 1866912449429504000 |
|---|---|
| author | Pražák, Aleš Kunešová, Marie Psutka, Josef |
| author_facet | Pražák, Aleš Kunešová, Marie Psutka, Josef |
| contents | Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based extension to an existing streaming ASR system to enable practical transcription of overlapping speech with minimal computational overhead. Our approach combines a speaker-independent (SI) model for standard operation with a speaker-conditioned (SC) model selectively applied in overlapping scenarios. Overlap detection is achieved using a compact binary classifier trained on frozen SI model output, offering accurate segmentation at negligible cost. The SC model employs Feature-wise Linear Modulation (FiLM) to incorporate speaker embeddings and is trained on synthetically mixed data to transcribe only the target speaker. Our method supports dynamic speaker tracking and reuses existing modules with minimal modifications. Evaluated on a challenging set of Czech television debates with 16% overlap, the system reduced WER on overlapping segments from 68.0% (baseline) to 35.78% while increasing total computational load by only 44%. The proposed system offers an effective and scalable solution for overlap transcription in continuous ASR services. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20288 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR Pražák, Aleš Kunešová, Marie Psutka, Josef Audio and Speech Processing Sound Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based extension to an existing streaming ASR system to enable practical transcription of overlapping speech with minimal computational overhead. Our approach combines a speaker-independent (SI) model for standard operation with a speaker-conditioned (SC) model selectively applied in overlapping scenarios. Overlap detection is achieved using a compact binary classifier trained on frozen SI model output, offering accurate segmentation at negligible cost. The SC model employs Feature-wise Linear Modulation (FiLM) to incorporate speaker embeddings and is trained on synthetically mixed data to transcribe only the target speaker. Our method supports dynamic speaker tracking and reuses existing modules with minimal modifications. Evaluated on a challenging set of Czech television debates with 16% overlap, the system reduced WER on overlapping segments from 68.0% (baseline) to 35.78% while increasing total computational load by only 44%. The proposed system offers an effective and scalable solution for overlap transcription in continuous ASR services. |
| title | Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2506.20288 |