VoiceX: A Text-To-Speech Framework for Custom Voices
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917755195752448 |
|---|---|
| author | Mertes, Silvan Don, Daksitha Withanage Grothe, Otto Kuch, Johanna Schlagowski, Ruben André, Elisabeth |
| author_facet | Mertes, Silvan Don, Daksitha Withanage Grothe, Otto Kuch, Johanna Schlagowski, Ruben André, Elisabeth |
| contents | Modern TTS systems are capable of creating highly realistic and natural-sounding speech. Despite these developments, the process of customizing TTS voices remains a complex task, mostly requiring the expertise of specialists within the field. One reason for this is the utilization of deep learning models, which are characterized by their expansive, non-interpretable parameter spaces, restricting the feasibility of manual customization. In this paper, we present a novel human-in-the-loop paradigm based on an evolutionary algorithm for directly interacting with the parameter space of a neural TTS model. We integrated our approach into a user-friendly graphical user interface that allows users to efficiently create original voices. Those voices can then be used with the backbone TTS model, for which we provide a Python API. Further, we present the results of a user study exploring the capabilities of VoiceX. We show that VoiceX is an appropriate tool for creating individual, custom voices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12170 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VoiceX: A Text-To-Speech Framework for Custom Voices Mertes, Silvan Don, Daksitha Withanage Grothe, Otto Kuch, Johanna Schlagowski, Ruben André, Elisabeth Human-Computer Interaction Sound Audio and Speech Processing Modern TTS systems are capable of creating highly realistic and natural-sounding speech. Despite these developments, the process of customizing TTS voices remains a complex task, mostly requiring the expertise of specialists within the field. One reason for this is the utilization of deep learning models, which are characterized by their expansive, non-interpretable parameter spaces, restricting the feasibility of manual customization. In this paper, we present a novel human-in-the-loop paradigm based on an evolutionary algorithm for directly interacting with the parameter space of a neural TTS model. We integrated our approach into a user-friendly graphical user interface that allows users to efficiently create original voices. Those voices can then be used with the backbone TTS model, for which we provide a Python API. Further, we present the results of a user study exploring the capabilities of VoiceX. We show that VoiceX is an appropriate tool for creating individual, custom voices. |
| title | VoiceX: A Text-To-Speech Framework for Custom Voices |
| topic | Human-Computer Interaction Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.12170 |