EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion

By Daxin Tan, Liqun Deng, Yu Ting Yeung, Xin Jiang, Xiao Chen, Tan Lee. 2021

55 citations recorded by the source corpus.

This paper presents the design, implementation and evaluation of a speech editing system, named EditSpeech, which allows a user to perform deletion, insertion and replacement of words in a given speech utterance, without causing audible degradation in speech quality and naturalness. The EditSpeech system is developed upon a neural text-to-speech (NTTS) synthesis framework. Partial inference and bidirectional fusion are proposed to effectively incorporate the contextual information related to the edited region and achieve smooth transition at both left and right boundaries. Distortion introduced to the unmodified parts of the utterance is alleviated. The EditSpeech system is developed and evaluated on English and Chinese in multi-speaker scenarios. Objective and subjective evaluation demonstrate that EditSpeech outperforms a few baseline systems in terms of low spectral distortion and preferred speech quality. Audio samples are available online for demonstration11https://daxintan-cuhk.github.io/EditSpeech/.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rongjie Huang
2. Zhou Zhao
3. Jinglin Liu
4. Yiwei Guo
5. Yi Ren
6. K. Yu
7. Ziyue Jiang
8. Zhijun Liu

In Signal Processing

1. Rongjie Huang
2. Jinglin Liu
3. Zhou Zhao
4. Yi Ren
5. Yiwei Guo
6. K. Yu
7. Zalán Borsos
8. Ziyue Jiang

Citations in the corpus

• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias (2023, methodology): “Moreover, Mega-TTS outperforms state-ofthe-art models on speech editing [52, 3] and cross-lingual TTS [67] tasks.”
• A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (2022, neutral): “Most recently, (Tan et al., 2021) use neural TTS model to generate better-modified speech.”
• SpeechPainter: Text-conditioned Speech Inpainting (2022, methodology): “Equipped with a duration predictor, the approach of [5] allows for insertion, replacement and deletion of segments of multiple seconds.”
• DiffVoice: Text-to-Speech with Latent Diffusion (2023, methodology): “We demonstrate that DiffVoice can achieve state-of-the-art performance on this task, without specially tailored model designs and training procedures adopted by many prior works [16– 19].”