Prosody: Models, Methods, and Applications

2021-08-01 · ACL 2021 5 · Nigel Ward, Gina-Anne Levow

Prosody is essential in human interaction, enabling people to show interest, establish rapport, efficiently convey nuances of attitude or intent, and so on. Some applications that exploit prosodic knowledge have recently shown superhuman performance, and in many respects our ability to effectively model prosody is rapidly advancing. This tutorial will overview the computational modeling of prosody, including recent advances and diverse actual and potential applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning

2021-10-27 · Shijun Wang, Dimche Kostadinov, Damian Borth

Voice Conversion (VC) for unseen speakers, also known as zero-shot VC, is an attractive research topic as it enables a range of applications like voice customizing, animation production, and others. Recent work in this a…

Disentanglement Representation Learning Voice Conversion

Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis

2021-07-27 · Shifeng Pan, Lei He

Cross-speaker style transfer is crucial to the applications of multi-style and expressive speech synthesis at scale. It does not require the target speakers to be experts in expressing all styles and to collect correspon…

Expressive Speech Synthesis Speech Synthesis Style Transfer text-to-speech+1

Speech BERT Embedding For Improving Prosody in Neural TTS

2021-06-08 · Liping Chen, Yan Deng, Xi Wang, Frank K. Soong 외

This paper presents a speech BERT model to extract embedded prosody information in speech segments for improving the prosody of synthesized speech in neural text-to-speech (TTS). As a pre-trained model, it can learn pros…

Decoder text-to-speech Text to Speech

DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training

2023-07-31 · Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee

Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to pred…

Denoising Expressive Speech Synthesis Speech Synthesis text-to-speech+1

ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech

2022-02-16 · Yi Ren, Ming Lei, Zhiying Huang, Shiliang Zhang 외

Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling w…

text-to-speech Text to Speech