ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929461727854592 |
|---|---|
| author | Halimeh, Mhd Modar Torcoli, Matteo Habets, Emanuël |
| author_facet | Halimeh, Mhd Modar Torcoli, Matteo Habets, Emanuël |
| contents | Dialogue separation involves isolating a dialogue signal from a mixture, such as a movie or a TV program. This can be a necessary step to enable dialogue enhancement for broadcast-related applications. In this paper, ConcateNet for dialogue separation is proposed, which is based on a novel approach for processing local and global features aimed at better generalization for out-of-domain signals. ConcateNet is trained using a noise reduction-focused, publicly available dataset and evaluated using three datasets: two noise reduction-focused datasets (in-domain), which show competitive performance for ConcateNet, and a broadcast-focused dataset (out-of-domain), which verifies the better generalization performance for the proposed architecture compared to considered state-of-the-art noise-reduction methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08729 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation Halimeh, Mhd Modar Torcoli, Matteo Habets, Emanuël Audio and Speech Processing Computation and Language Sound Dialogue separation involves isolating a dialogue signal from a mixture, such as a movie or a TV program. This can be a necessary step to enable dialogue enhancement for broadcast-related applications. In this paper, ConcateNet for dialogue separation is proposed, which is based on a novel approach for processing local and global features aimed at better generalization for out-of-domain signals. ConcateNet is trained using a noise reduction-focused, publicly available dataset and evaluated using three datasets: two noise reduction-focused datasets (in-domain), which show competitive performance for ConcateNet, and a broadcast-focused dataset (out-of-domain), which verifies the better generalization performance for the proposed architecture compared to considered state-of-the-art noise-reduction methods. |
| title | ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation |
| topic | Audio and Speech Processing Computation and Language Sound |
| url | https://arxiv.org/abs/2408.08729 |