Xinhui Hu
10 papers · 2007–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Academic Marathon Β· Full π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver 𧬠Topic Evolution
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Deep Learning
(7)
Speech & Audio
(7)
Machine Learning
(4)
Natural Language Processing
(4)
Architectures
(4)
Learning Types
(4)
Processing
(3)
Recognition
(3)
Application Areas
(2)
Generation
(2)
Resources & Methods
(2)
Artificial Intelligence
(1)
Applications
(1)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
automatic speech recognition
(2)
feature extraction
(1)
diffusion model
(1)
data augmentation
(1)
speech recognition
(1)
neural machine translation
(1)
text generation
(1)
cross-modal learning
(1)
transformer network
(1)
language identification
(1)
adversarial training
(1)
speech enhancement
(1)
connectionist temporal classification
(1)
semantic information
(1)
attention mechanism
(1)
long short-term memory
(1)
language model
(1)
mixture of expert
(1)
transfer learning
(1)
representation learning
(1)
Papers
A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model
Interspeech 2025
Discrete Audio Representations for Automated Audio Captioning
Interspeech 2025
RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval
Interspeech 2025
Speaker Normalization and Content Restoration for Zero-Shot Voice Conversion with Attention-Enhanced Discriminator
Interspeech 2025
SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR
Interspeech 2024
Hybrid-Regressive Paradigm for Accurate and Speed-Robust Neural Machine Translation
ACL 2023
Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition
Interspeech 2022
An End-to-End Dialect Identification System with Transfer Learning from a Multilingual Automatic Speech Recognition Model
Interspeech 2021
Data Augmentation for Code-Switch Language Modeling by Fusing Multiple Text Generation Methods
Interspeech 2020
Learning Unsupervised SVM Classifier for Answer Selection in Web Question Answering
EMNLP 2007