Hexin Liu
13 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (8) πΊοΈ Taxonomy Completionist (23) π Conference Polyglot (4)
π
Cross-Pollinator
(8)
π
Academic Marathon
(5)
π
Century Club
(10)
π₯
Unstoppable
(5)
Conferences
INTERSPEECH (6)
ACL (3)
EMNLP (2)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
language identification
(4)
language diarization
(3)
retrieval-augmented generation
(2)
self-supervised learning
(2)
depression detection
(2)
equal error rate
(2)
speech processing
(1)
speaker embedding
(1)
model evaluation
(1)
wavelet transform
(1)
inference speedup
(1)
child-directed speech
(1)
diffusion model
(1)
convolutional neural network
(1)
speech synthesis
(1)
algorithmic bia
(1)
training acceleration
(1)
automatic speech recognition
(1)
error rate
(1)
multimodal learning
(1)
Papers
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
ACL 2026
Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR
AAAI 2026
Evaluating the Expressive Appropriateness of Speech in Rich Contexts
ACL 2026
SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information
ACL 2025
GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling
ICLR 2025
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
EMNLP 2024
Bridging Child-Centered Speech Language Identification and Language Diarization via Phonetics
INTERSPEECH 2024
Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model
EMNLP 2024
Investigating model performance in language identification: beyond simple error statistics
INTERSPEECH 2023
Self-supervised Learning Representation based Accent Recognition with Persistent Accent Memory
INTERSPEECH 2023
MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization
INTERSPEECH 2023
PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification
INTERSPEECH 2022
End-to-End Language Diarization for Bilingual Code-Switching Speech
INTERSPEECH 2021