A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS)
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_ | 1866909003610587136 |
|---|---|
| author | Ho, Chun-wei Siniscalchi, Sabato Marco Li, Kai Lee, Chin-Hui |
| author_facet | Ho, Chun-wei Siniscalchi, Sabato Marco Li, Kai Lee, Chin-Hui |
| contents | We propose a knowledge-driven approach to speech target extraction in the presence of background sound effects already recorded in cinematic audio. The specific knowledge sources studied are manners of articulation that are detected in speech frames and adopted to form a knowledge vector as a part of features to enhance speech separation and target speech extraction because some short speech segments are often difficult to separate from mixed background sounds. Testing on the recent Sound Demixing Challenge data for cinematic audio source separation (CASS) shows that utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27403 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS) Ho, Chun-wei Siniscalchi, Sabato Marco Li, Kai Lee, Chin-Hui Audio and Speech Processing We propose a knowledge-driven approach to speech target extraction in the presence of background sound effects already recorded in cinematic audio. The specific knowledge sources studied are manners of articulation that are detected in speech frames and adopted to form a knowledge vector as a part of features to enhance speech separation and target speech extraction because some short speech segments are often difficult to separate from mixed background sounds. Testing on the recent Sound Demixing Challenge data for cinematic audio source separation (CASS) shows that utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events. |
| title | A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS) |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2604.27403 |