LoRP-TTS: Low-Rank Personalized Text-To-Speech

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bondaruk, Łukasz, Kubiak, Jakub
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