EdiTTS: Score-based Editing for Controllable Text-to-Speech
Preprint
Abstract
We present EdiTTS, an off-the-shelf speech editing methodology based on score-based generative modeling for text-to-speech synthesis. EdiTTS allows for targeted, granular editing of audio, both in terms of content and pitch, without the need for any additional training, task-specific optimization, or architectural modifications to the score-based model backbone. Specifically, we apply coarse yet deliberate perturbations in the Gaussian prior space to induce desired behavior from the diffusion model while applying masks and softening kernels to ensure that iterative edits are applied only to the target region. Through listening tests and speech-to-text back transcription, we show that EdiTTS outperforms existing baselines and produces robust samples that satisfy user-imposed requirements.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- One TTS Alignment to Rule Them All2022
- EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion2021
- ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models2021
- Diff-TTS: A Denoising Diffusion Model for Text-to-Speech2021
- Fastpitch: Parallel Text-to-Speech with Pitch Prediction2021
- Context-Aware Prosody Correction for Text-Based Speech Editing2021
- Crepe: A Convolutional Representation for Pitch Estimation2018
- VoCoACM Transactions on Graphics, 2017
- WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time ApplicationsIEICE Transactions on Information and Systems, 2016
- Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphonesSpeech Communication, 1990