Desheng Hu

4 papers · 2022–2025 · 1 venue · 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 ↓

🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (11)

Venues

Interspeech (4)

Top co-authors

Xinhui Hu (4) Xinkang Xu (3) Jingguang Tian (2) Yang Xiang (2) Jian Lu (1) Jiabei He (1) Haoqin Sun (1) Shiwan Zhao (1) Hui Wang (1) Chao Zhang (1)

Research topics

Deep Learning (4) Speech & Audio (3) Architectures (2) Learning Types · Deep Learning (2) Processing (2) Machine Learning (1) Natural Language Processing (1) Core Methods (1) Learning Types · Machine Learning (1) Models (1) Resources & Methods (1) Synthesis (1)

Keywords

feature extraction (1) attention mechanism (1) cross-modal learning (1) adversarial training (1) speech enhancement (1) semantic information (1) diffusion model (1) long short-term memory (1) transformer network (1) residual network (1) zero-shot voice conversion (1) speech emotion recognition (1) speech retrieval (1) speaker normalization (1) contrastive language-audio pretraining (1) content restoration (1) emotional speaking style (1) factorized codec (1)

Papers

A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model 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 Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition Interspeech 2022