Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912008891269120 |
|---|---|
| author | Horiguchi, Shota Ando, Atsushi Moriya, Takafumi Ashihara, Takanori Sato, Hiroshi Tawara, Naohiro Delcroix, Marc |
| author_facet | Horiguchi, Shota Ando, Atsushi Moriya, Takafumi Ashihara, Takanori Sato, Hiroshi Tawara, Naohiro Delcroix, Marc |
| contents | This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker speech applications such as speaker diarization and target-speaker speech processing. Despite the challenges of obtaining a single speaker's speech without pre-registration in multi-speaker scenarios, most studies on speaker embedding extraction focus on extracting embeddings only from single-speaker recordings. Some methods have been proposed for extracting speaker embeddings directly from multi-speaker recordings, but they typically require preparing a model for each possible number of speakers or involve complicated training procedures. The proposed method computes the embeddings of multiple speakers by focusing on different parts of the frame-wise embeddings extracted from the input multi-speaker audio. This is achieved by recursively computing attention weights for pooling the frame-wise embeddings. Additionally, we propose using the calculated attention weights to estimate the number of speakers in the recording, which allows the same model to be applied to various numbers of speakers. Experimental evaluations demonstrate the effectiveness of the proposed method in speaker verification and diarization tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17142 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings Horiguchi, Shota Ando, Atsushi Moriya, Takafumi Ashihara, Takanori Sato, Hiroshi Tawara, Naohiro Delcroix, Marc Audio and Speech Processing Sound This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker speech applications such as speaker diarization and target-speaker speech processing. Despite the challenges of obtaining a single speaker's speech without pre-registration in multi-speaker scenarios, most studies on speaker embedding extraction focus on extracting embeddings only from single-speaker recordings. Some methods have been proposed for extracting speaker embeddings directly from multi-speaker recordings, but they typically require preparing a model for each possible number of speakers or involve complicated training procedures. The proposed method computes the embeddings of multiple speakers by focusing on different parts of the frame-wise embeddings extracted from the input multi-speaker audio. This is achieved by recursively computing attention weights for pooling the frame-wise embeddings. Additionally, we propose using the calculated attention weights to estimate the number of speakers in the recording, which allows the same model to be applied to various numbers of speakers. Experimental evaluations demonstrate the effectiveness of the proposed method in speaker verification and diarization tasks. |
| title | Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2408.17142 |