Two-pass Endpoint Detection for Speech Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914652212953088 |
|---|---|
| author | Raju, Anirudh Khare, Aparna He, Di Sklyar, Ilya Chen, Long Alptekin, Sam Trinh, Viet Anh Zhang, Zhe Vaz, Colin Ravichandran, Venkatesh Maas, Roland Rastrow, Ariya |
| author_facet | Raju, Anirudh Khare, Aparna He, Di Sklyar, Ilya Chen, Long Alptekin, Sam Trinh, Viet Anh Zhang, Zhe Vaz, Colin Ravichandran, Venkatesh Maas, Roland Rastrow, Ariya |
| contents | Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08916 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Two-pass Endpoint Detection for Speech Recognition Raju, Anirudh Khare, Aparna He, Di Sklyar, Ilya Chen, Long Alptekin, Sam Trinh, Viet Anh Zhang, Zhe Vaz, Colin Ravichandran, Venkatesh Maas, Roland Rastrow, Ariya Audio and Speech Processing Sound Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used. |
| title | Two-pass Endpoint Detection for Speech Recognition |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2401.08916 |