LoRP-TTS: Low-Rank Personalized Text-To-Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917918828134400 |
|---|---|
| author | Bondaruk, Łukasz Kubiak, Jakub |
| author_facet | Bondaruk, Łukasz Kubiak, Jakub |
| contents | Speech synthesis models convert written text into natural-sounding audio. While earlier models were limited to a single speaker, recent advancements have led to the development of zero-shot systems that generate realistic speech from a wide range of speakers using their voices as additional prompts. However, they still struggle with imitating non-studio-quality samples that differ significantly from the training datasets. In this work, we demonstrate that utilizing Low-Rank Adaptation (LoRA) allows us to successfully use even single recordings of spontaneous speech in noisy environments as prompts. This approach enhances speaker similarity by up to $30pp$ while preserving content and naturalness. It represents a significant step toward creating truly diverse speech corpora, that is crucial in all speech-related tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LoRP-TTS: Low-Rank Personalized Text-To-Speech Bondaruk, Łukasz Kubiak, Jakub Sound Artificial Intelligence Audio and Speech Processing Speech synthesis models convert written text into natural-sounding audio. While earlier models were limited to a single speaker, recent advancements have led to the development of zero-shot systems that generate realistic speech from a wide range of speakers using their voices as additional prompts. However, they still struggle with imitating non-studio-quality samples that differ significantly from the training datasets. In this work, we demonstrate that utilizing Low-Rank Adaptation (LoRA) allows us to successfully use even single recordings of spontaneous speech in noisy environments as prompts. This approach enhances speaker similarity by up to $30pp$ while preserving content and naturalness. It represents a significant step toward creating truly diverse speech corpora, that is crucial in all speech-related tasks. |
| title | LoRP-TTS: Low-Rank Personalized Text-To-Speech |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2502.07562 |