Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05106 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909569295319040 |
|---|---|
| author | Brade, Stephen Anderson, Sam Kumar, Rithesh Jin, Zeyu Truong, Anh |
| author_facet | Brade, Stephen Anderson, Sam Kumar, Rithesh Jin, Zeyu Truong, Anh |
| contents | Novice content creators often invest significant time recording expressive speech for social media videos. While recent advancements in text-to-speech (TTS) technology can generate highly realistic speech in various languages and accents, many struggle with unintuitive or overly granular TTS interfaces. We propose simplifying TTS generation by allowing users to specify high-level context alongside their script. Our Wizard-of-Oz system, SpeakEasy, leverages user-provided context to inform and influence TTS output, enabling iterative refinement with high-level feedback. This approach was informed by two 8-subject formative studies: one examining content creators' experiences with TTS, and the other drawing on effective strategies from voice actors. Our evaluation shows that participants using SpeakEasy were more successful in generating performances matching their personal standards, without requiring significantly more effort than leading industry interfaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05106 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation Brade, Stephen Anderson, Sam Kumar, Rithesh Jin, Zeyu Truong, Anh Human-Computer Interaction Artificial Intelligence Machine Learning Novice content creators often invest significant time recording expressive speech for social media videos. While recent advancements in text-to-speech (TTS) technology can generate highly realistic speech in various languages and accents, many struggle with unintuitive or overly granular TTS interfaces. We propose simplifying TTS generation by allowing users to specify high-level context alongside their script. Our Wizard-of-Oz system, SpeakEasy, leverages user-provided context to inform and influence TTS output, enabling iterative refinement with high-level feedback. This approach was informed by two 8-subject formative studies: one examining content creators' experiences with TTS, and the other drawing on effective strategies from voice actors. Our evaluation shows that participants using SpeakEasy were more successful in generating performances matching their personal standards, without requiring significantly more effort than leading industry interfaces. |
| title | SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.05106 |