◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Hui Lu

HCCL, The Chinese University of Hong Kong

4 papers hereh-index 9264 citations19 works total

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

author position
  • first author1
  • middle author3

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.SD2
  • cs.CL1
  • eess.AS1
affiliations
  • HCCL, The Chinese University of Hong Kong
ORCID 0000-0002-7698-6262
same name
  • Hui Lu — 7 papers, h 3
  • Hui Lu — 6 papers, h 4
  • Hui Lu — 3 papers, h 3
  • Hui Lu — 2 papers, h 2
  • Hui Lu — 2 papers, h 4
  • Hui Lu — 1 paper, h 4

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

collaborators

4 papers

cs.SD2026

Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization

Shuhai Peng, Jinjiang Liu, Hui Lu +5

Generative streaming models for Target Speaker Extraction (TSE) commonly exhibit a quality--intelligibility trade-off, wherein naive optimization for perceptual audio quality tends…

cs.SD2026

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

Shuhai Peng, Hui Lu, Jinjiang Liu +8

While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications. Direc…

eess.AS2026

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis

Huimeng Wang, Hui Lu, Jiajun Deng +7

Continuous autoregressive speech synthesis has recently emerged as a promising direction for zero-shot text-to-speech (TTS). However, existing methods still suffer from a fundament…

cs.CL2026

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

Hui Lu, Xueyuan Chen, Huimeng Wang +4

Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to…

◍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.