Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.11535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913993381117952 |
|---|---|
| author | Prabhu, Navin Raj de Oliveira, Danilo Lehmann-Willenbrock, Nale Gerkmann, Timo |
| author_facet | Prabhu, Navin Raj de Oliveira, Danilo Lehmann-Willenbrock, Nale Gerkmann, Timo |
| contents | Speech Emotion Conversion aims to modify the emotion expressed in input speech while preserving lexical content and speaker identity. Recently, generative modeling approaches have shown promising results in changing local acoustic properties such as fundamental frequency, spectral envelope and energy, but often lack the ability to control the duration of sounds. To address this, we propose a duration modeling framework using resynthesis-based discrete content representations, enabling modification of speech duration to reflect target emotions and achieve controllable speech rates without using parallel data. Experimental results reveal that the inclusion of the proposed duration modeling framework significantly enhances emotional expressiveness, in the in-the-wild MSP-Podcast dataset. Analyses show that low-arousal emotions correlate with longer durations and slower speech rates, while high-arousal emotions produce shorter, faster speech. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11535 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling Prabhu, Navin Raj de Oliveira, Danilo Lehmann-Willenbrock, Nale Gerkmann, Timo Audio and Speech Processing Speech Emotion Conversion aims to modify the emotion expressed in input speech while preserving lexical content and speaker identity. Recently, generative modeling approaches have shown promising results in changing local acoustic properties such as fundamental frequency, spectral envelope and energy, but often lack the ability to control the duration of sounds. To address this, we propose a duration modeling framework using resynthesis-based discrete content representations, enabling modification of speech duration to reflect target emotions and achieve controllable speech rates without using parallel data. Experimental results reveal that the inclusion of the proposed duration modeling framework significantly enhances emotional expressiveness, in the in-the-wild MSP-Podcast dataset. Analyses show that low-arousal emotions correlate with longer durations and slower speech rates, while high-arousal emotions produce shorter, faster speech. |
| title | Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.11535 |