DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911586547924992 |
|---|---|
| author | Nakata, Wataru Saito, Yuki Yamauchi, Kazuki Tsunoo, Emiru Saruwatari, Hiroshi |
| author_facet | Nakata, Wataru Saito, Yuki Yamauchi, Kazuki Tsunoo, Emiru Saruwatari, Hiroshi |
| contents | Full-duplex dialogue audio, in which each speaker is recorded on a separate track, is an important resource for spoken dialogue research, but is difficult to collect at scale. Most in-the-wild two-speaker dialogue is available only as degraded monaural mixtures, making it unsuitable for systems requiring clean speaker-wise signals. We propose DialogueSidon, a model for joint restoration and separation of degraded monaural two-speaker dialogue audio. DialogueSidon combines a variational autoencoder (VAE) operates on the speech self-supervised learning (SSL) model feature, which compresses SSL model features into a compact latent space, with a diffusion-based latent predictor that recovers speaker-wise latent representations from the degraded mixture. Experiments on English, multilingual, and in-the-wild dialogue datasets show that DialogueSidon substantially improves intelligibility and separation quality over a baseline, while also achieving much faster inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09344 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio Nakata, Wataru Saito, Yuki Yamauchi, Kazuki Tsunoo, Emiru Saruwatari, Hiroshi Sound Audio and Speech Processing Full-duplex dialogue audio, in which each speaker is recorded on a separate track, is an important resource for spoken dialogue research, but is difficult to collect at scale. Most in-the-wild two-speaker dialogue is available only as degraded monaural mixtures, making it unsuitable for systems requiring clean speaker-wise signals. We propose DialogueSidon, a model for joint restoration and separation of degraded monaural two-speaker dialogue audio. DialogueSidon combines a variational autoencoder (VAE) operates on the speech self-supervised learning (SSL) model feature, which compresses SSL model features into a compact latent space, with a diffusion-based latent predictor that recovers speaker-wise latent representations from the degraded mixture. Experiments on English, multilingual, and in-the-wild dialogue datasets show that DialogueSidon substantially improves intelligibility and separation quality over a baseline, while also achieving much faster inference. |
| title | DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2604.09344 |