Papers by Zhisheng Zheng

4 papers
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for speech emotion recognition are not suitable for emotional tasks.
Approach: They propose a universal speech emotion representation model that is pre-trained on open-source emotion data.
Outcome: euphoria2vec outperforms state-of-the-art models and emotion specialist models . it shows consistent improvements among 10 different languages of speech emotion recognition datasets .
VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation (2026.findings-acl)

Copied to clipboard

Challenge: Neural codec language models (NCLMs) lack fine-grained controllability and inability to extrapolate to sequence lengths much longer than those seen during training.
Approach: They propose a novel autoregressive encoder-decoder neural codec language model that can be trained with a Continuation-Prompt Mixed training system.
Outcome: The proposed model outperforms or is on par with current state-of-the-art models on short-form benchmarks such as LibriSpeech and Seed-TTS in terms of intelligibility and naturalness.
Scaling Rich Style-Prompted Text-to-Speech Datasets (2025.emnlp-main)

Copied to clipboard

Challenge: Existing datasets that only cover basic tags are limited in their scale or coverage of style tags.
Approach: They propose a large-scale dataset that annotates speech utterances with rich style captions.
Outcome: The proposed dataset scales speech utterances with rich style captions for the first time.
VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing (2025.emnlp-main)

Copied to clipboard

Challenge: Autoregressive language model for multilingual speech editing and zero-shot text-to-speech synthesis is available in 11 languages.
Approach: They introduce an autoregressive neural codec language model which unifies multilingual speech editing and zero-shot text-to-speech synthesis across 11 languages.
Outcome: The model generates high-quality, natural-sounding speech, even with limited per-language data . it shows robust performance in diverse linguistic settings, even in limited per language data compared to other models .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations