Automatic Voice Identification after Speech Resynthesis using PPG
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_ | 1866929449757310976 |
|---|---|
| author | Gaudier, Thibault Tahon, Marie Larcher, Anthony Estève, Yannick |
| author_facet | Gaudier, Thibault Tahon, Marie Larcher, Anthony Estève, Yannick |
| contents | Speech resynthesis is a generic task for which we want to synthesize audio with another audio as input, which finds applications for media monitors and journalists.Among different tasks addressed by speech resynthesis, voice conversion preserves the linguistic information while modifying the identity of the speaker, and speech edition preserves the identity of the speaker but some words are modified.In both cases, we need to disentangle speaker and phonetic contents in intermediate representations.Phonetic PosteriorGrams (PPG) are a frame-level probabilistic representation of phonemes, and are usually considered speaker-independent.This paper presents a PPG-based speech resynthesis system.A perceptive evaluation assesses that it produces correct audio quality.Then, we demonstrate that an automatic speaker verification model is not able to recover the source speaker after re-synthesis with PPG, even when the model is trained on synthetic data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02712 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic Voice Identification after Speech Resynthesis using PPG Gaudier, Thibault Tahon, Marie Larcher, Anthony Estève, Yannick Sound Artificial Intelligence Neural and Evolutionary Computing Audio and Speech Processing Signal Processing Speech resynthesis is a generic task for which we want to synthesize audio with another audio as input, which finds applications for media monitors and journalists.Among different tasks addressed by speech resynthesis, voice conversion preserves the linguistic information while modifying the identity of the speaker, and speech edition preserves the identity of the speaker but some words are modified.In both cases, we need to disentangle speaker and phonetic contents in intermediate representations.Phonetic PosteriorGrams (PPG) are a frame-level probabilistic representation of phonemes, and are usually considered speaker-independent.This paper presents a PPG-based speech resynthesis system.A perceptive evaluation assesses that it produces correct audio quality.Then, we demonstrate that an automatic speaker verification model is not able to recover the source speaker after re-synthesis with PPG, even when the model is trained on synthetic data. |
| title | Automatic Voice Identification after Speech Resynthesis using PPG |
| topic | Sound Artificial Intelligence Neural and Evolutionary Computing Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2408.02712 |