Robust Speech Activity Detection in the Presence of Singing Voice
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917137104240640 |
|---|---|
| author | Grundhuber, Philipp Halimeh, Mhd Modar Strauß, Martin Habets, Emanuël A. P. |
| author_facet | Grundhuber, Philipp Halimeh, Mhd Modar Strauß, Martin Habets, Emanuël A. P. |
| contents | Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recognition. We introduce Singing-Robust Speech Activity Detection ( SR-SAD ), a neural network designed to robustly detect speech in the presence of singing. Our key contributions are: i) a training strategy using controlled ratios of speech and singing samples to improve discrimination, ii) a computationally efficient model that maintains robust performance while reducing inference runtime, and iii) a new evaluation metric tailored to assess SAD robustness in mixed speech-singing scenarios. Experiments on a challenging dataset spanning multiple musical genres show that SR-SAD maintains high speech detection accuracy (AUC = 0.919) while rejecting singing. By explicitly learning to distinguish between speech and singing, SR-SAD enables more reliable SAD in mixed speech-singing scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09713 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Speech Activity Detection in the Presence of Singing Voice Grundhuber, Philipp Halimeh, Mhd Modar Strauß, Martin Habets, Emanuël A. P. Audio and Speech Processing Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recognition. We introduce Singing-Robust Speech Activity Detection ( SR-SAD ), a neural network designed to robustly detect speech in the presence of singing. Our key contributions are: i) a training strategy using controlled ratios of speech and singing samples to improve discrimination, ii) a computationally efficient model that maintains robust performance while reducing inference runtime, and iii) a new evaluation metric tailored to assess SAD robustness in mixed speech-singing scenarios. Experiments on a challenging dataset spanning multiple musical genres show that SR-SAD maintains high speech detection accuracy (AUC = 0.919) while rejecting singing. By explicitly learning to distinguish between speech and singing, SR-SAD enables more reliable SAD in mixed speech-singing scenarios. |
| title | Robust Speech Activity Detection in the Presence of Singing Voice |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2512.09713 |