DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929368693997568 |
|---|---|
| author | Landini, Federico Diez, Mireia Stafylakis, Themos Burget, Lukáš |
| author_facet | Landini, Federico Diez, Mireia Stafylakis, Themos Burget, Lukáš |
| contents | Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most successful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and faster inference time. Furthermore, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04324 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors Landini, Federico Diez, Mireia Stafylakis, Themos Burget, Lukáš Audio and Speech Processing Sound Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most successful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and faster inference time. Furthermore, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data. |
| title | DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2312.04324 |