# DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning

arXiv: https://arxiv.org/abs/2203.15683 · HTML: https://mlsanity.com/paper/2203.15683/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2022.

## Built on by (most cited first, 2 of 2)

- [XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech](https://mlsanity.com/paper/2305.19709/) (2023)
- [Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters](https://mlsanity.com/paper/2401.05111/) (2024)

## Abstract (arXiv)

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech corpora as training data. However, they only address either time-invariant or time-variant noises. We propose a degradation-robust TTS method, which can be trained on speech corpora that contain both additive noises and environmental distortions. It jointly represents the time-variant additive noises with a frame-level encoder and the time-invariant environmental distortions with an utterance-level encoder. We also propose a regularization method to attain clean environmental embedding that is disentangled from the utterance-dependent information such as linguistic contents and speaker characteristics. Evaluation results show that our method achieved significantly higher-quality synthetic speech than previous methods in the condition including both additive noise and reverberation.