Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AL47WG6QT" target="_blank" >RIV/00216208:11320/26:L47WG6QT - isvavai.cz</a>

Result on the web

<a href="http://arxiv.org/abs/2501.14273" target="_blank" >http://arxiv.org/abs/2501.14273</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2501.14273" target="_blank" >10.48550/arXiv.2501.14273</a>

Result language

angličtina

Original language name

Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models

Original language description

Recently, emotional speech generation and speaker cloning have garnered significant interest in text-to-speech (TTS). With the open-sourcing of codec language TTS models trained on massive datasets with large-scale parameters, adapting these general pre-trained TTS models to generate speech with specific emotional expressions and target speaker characteristics has become a topic of great attention. Common approaches, such as full and adapter-based fine-tuning, often overlook the specific contributions of model parameters to emotion and speaker control. Treating all parameters uniformly during fine-tuning, especially when the target data has limited content diversity compared to the pre-training corpus, results in slow training speed and an increased risk of catastrophic forgetting. To address these challenges, we propose a characteristic-specific partial fine-tuning strategy, short as CSP-FT. First, we use a weighted-sum approach to analyze the contributions of different Transformer layers in a pre-trained codec language TTS model for emotion and speaker control in the generated speech. We then selectively fine-tune the layers with the highest and lowest characteristic-specific contributions to generate speech with target emotional expression and speaker identity. Experimental results demonstrate that our method achieves performance comparable to, or even surpassing, full fine-tuning in generating speech with specific emotional expressions and speaker identities. Additionally, CSP-FT delivers approximately 2x faster training speeds, fine-tunes only around 8% of parameters, and significantly reduces catastrophic forgetting. Furthermore, we show that codec language TTS models perform competitively with self-supervised models in speaker identification and emotion classification tasks, offering valuable insights for developing universal speech processing models.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů