◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Zehai Tu

3 papers here

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author2
  • middle author1

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.SD2
  • eess.AS1
same name
  • Zehai Tu — 3 papers, h 7
  • Zehai Tu — 1 paper

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

most citedEnergy-Based Models For Speech Synthesis

2 citations · 3 across the 3 of their papers we have counts for

collaborators

3 papers

cs.SD2024

Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis

Zehai Tu, Guangyan Zhang, Yiting Lu +3

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Altho…

eess.AS2023★ 1 cited

Intelligibility prediction with a pretrained noise-robust automatic speech recognition model

Zehai Tu, Ning Ma, Jon Barker

This paper describes two intelligibility prediction systems derived from a pretrained noise-robust automatic speech recognition (ASR) model for the second Clarity Prediction Challe…

cs.SD2023★ 2 cited

Energy-Based Models For Speech Synthesis

Wanli Sun, Zehai Tu, Anton Ragni

Recently there has been a lot of interest in non-autoregressive (non-AR) models for speech synthesis, such as FastSpeech 2 and diffusion models. Unlike AR models, these models do n…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.