Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909190157500416 |
|---|---|
| author | von Neumann, Thilo Boeddeker, Christoph Cord-Landwehr, Tobias Delcroix, Marc Haeb-Umbach, Reinhold |
| author_facet | von Neumann, Thilo Boeddeker, Christoph Cord-Landwehr, Tobias Delcroix, Marc Haeb-Umbach, Reinhold |
| contents | We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet separation architecture, followed by a speaker-agnostic speech recognizer, we achieve state-of-the-art recognition performance in terms of Optimal Reference Combination Word Error Rate (ORC WER). Then, a d-vector-based diarization module is employed to extract speaker embeddings from the enhanced signals and to assign the CSS outputs to the correct speaker. Here, we propose a syntactically informed diarization using sentence- and word-level boundaries of the ASR module to support speaker turn detection. This results in a state-of-the-art Concatenated minimum-Permutation Word Error Rate (cpWER) for the full meeting recognition pipeline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_16482 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization von Neumann, Thilo Boeddeker, Christoph Cord-Landwehr, Tobias Delcroix, Marc Haeb-Umbach, Reinhold Audio and Speech Processing Sound We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet separation architecture, followed by a speaker-agnostic speech recognizer, we achieve state-of-the-art recognition performance in terms of Optimal Reference Combination Word Error Rate (ORC WER). Then, a d-vector-based diarization module is employed to extract speaker embeddings from the enhanced signals and to assign the CSS outputs to the correct speaker. Here, we propose a syntactically informed diarization using sentence- and word-level boundaries of the ASR module to support speaker turn detection. This results in a state-of-the-art Concatenated minimum-Permutation Word Error Rate (cpWER) for the full meeting recognition pipeline. |
| title | Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2309.16482 |