Hexin Liu

Orcid: 0000-0002-3998-9229

According to our database1, Hexin Liu authored at least 17 papers between 2013 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection.
CoRR, 2024

Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model.
CoRR, 2024

2023
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors.
CoRR, 2023

Generative error correction for code-switching speech recognition using large language models.
CoRR, 2023

Enhancing Code-switching Speech Recognition with Interactive Language Biases.
CoRR, 2023

Unidirectional brain-computer interface: Artificial neural network encoding natural images to fMRI response in the visual cortex.
CoRR, 2023

Investigating model performance in language identification: beyond simple error statistics.
CoRR, 2023

A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extracters.
Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023), 2023

Reducing Language Confusion for Code-Switching Speech Recognition with Token-Level Language Diarization.
Proceedings of the IEEE International Conference on Acoustics, 2023

PQLM - Multilingual Decentralized Portable Quantum Language Model.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
Efficient Self-Supervised Learning Representations for Spoken Language Identification.
IEEE J. Sel. Top. Signal Process., 2022

PQLM - Multilingual Decentralized Portable Quantum Language Model for Privacy Protection.
CoRR, 2022

Enhance Language Identification using Dual-mode Model with Knowledge Distillation.
CoRR, 2022

Enhancing Language Identification Using Dual-Mode Model with Knowledge Distillation.
Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June, 2022

PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification.
Proceedings of the Interspeech 2022, 2022

2021
End-to-End Language Diarization for Bilingual Code-Switching Speech.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

2013
Radio-over-Fibre access for sustainable Digital Cities.
Ann. des Télécommunications, 2013


  Loading...