EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
Authors:
Preprint
Abstract
Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech that are hard to transcribe (prosody, voice styles, non-verbal vocalization). The adoption of these methods is still limited by the fact that most speech synthesis datasets are read, severely limiting spontaneity and expressivity. Here, we introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis that includes both read speech and improvised dialogues rendered in 26 spontaneous expressive styles. We illustrate the challenges and potentials of this dataset with an expressive resynthesis benchmark where the task is to encode the input in low-bitrate units and resynthesize it in a target voice while preserving content and style. We evaluate resynthesis quality with automatic metrics for different self-supervised discrete encoders, and explore tradeoffs between quality, bitrate and invariance to speaker and style. All the dataset, evaluation metrics and baseline models are open sourceKeywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersIEEE Transactions on Audio, Speech and Language Processing, 2025
- Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal SupervisionTransactions of the Association for Computational Linguistics, 2023
- AudioLM: A Language Modeling Approach to Audio GenerationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Regeneration2023
- w2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training2021
- SoundStream: An End-to-End Neural Audio CodecIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Self-Training and Pre-Training are Complementary for Speech Recognition2021
- Libri-Light: A Benchmark for ASR with Limited or No Supervision2020
- Librispeech: An ASR corpus based on public domain audio books2015