MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
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_ | 1866916283030700032 |
|---|---|
| author | Kim, Seung-bin Lim, Chan-yeong Heo, Jungwoo Kim, Ju-ho Shin, Hyun-seo Koo, Kyo-Won Yu, Ha-Jin |
| author_facet | Kim, Seung-bin Lim, Chan-yeong Heo, Jungwoo Kim, Ju-ho Shin, Hyun-seo Koo, Kyo-Won Yu, Ha-Jin |
| contents | In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this obstacle, we propose a novel structure, MR-RawNet, designed to enhance the robustness of speaker verification systems against variable duration utterances using raw waveforms. The MR-RawNet extracts time-frequency representations from raw waveforms via a multi-resolution feature extractor that optimally adjusts both temporal and spectral resolutions simultaneously. Furthermore, we apply a multi-resolution attention block that focuses on diverse and extensive temporal contexts, ensuring robustness against changes in utterance length. The experimental results, conducted on VoxCeleb1 dataset, demonstrate that the MR-RawNet exhibits superior performance in handling utterances of variable duration compared to other raw waveform-based systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07103 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms Kim, Seung-bin Lim, Chan-yeong Heo, Jungwoo Kim, Ju-ho Shin, Hyun-seo Koo, Kyo-Won Yu, Ha-Jin Audio and Speech Processing Artificial Intelligence In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this obstacle, we propose a novel structure, MR-RawNet, designed to enhance the robustness of speaker verification systems against variable duration utterances using raw waveforms. The MR-RawNet extracts time-frequency representations from raw waveforms via a multi-resolution feature extractor that optimally adjusts both temporal and spectral resolutions simultaneously. Furthermore, we apply a multi-resolution attention block that focuses on diverse and extensive temporal contexts, ensuring robustness against changes in utterance length. The experimental results, conducted on VoxCeleb1 dataset, demonstrate that the MR-RawNet exhibits superior performance in handling utterances of variable duration compared to other raw waveform-based systems. |
| title | MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2406.07103 |