Chengxi Deng

5 papers · 2025–2025 · 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 (13) ⭐ Rising Star (5) ⚡ Prolific Year · Productive

Venues

Interspeech (5)

Top co-authors

Mengzhe Geng (4) Guinan Li (4) Xunying Liu (4) Huimeng Wang (4) Youjun Chen (3) Haoning Xu (3) Shujie Hu (3) Xurong Xie (3) Mingyu Cui (2) Jiankun Zhao (2)

Research topics

Speech & Audio (5) Artificial Intelligence (3) Deep Learning (3) Core AI · Artificial Intelligence (3) Learning Types (3) Recognition (3) Analysis (2) Computer Vision (1) Security & Privacy (1) Architectures (1) Core AI · Computer Vision (1) Privacy (1) Synthesis (1)

Keywords

word error rate (3) speech foundation model (2) mixture of expert (2) speaker adaptation (2) zero-shot adaptation (2) model pruning (1) audio watermarking (1) prompt tuning (1) speaker identity (1) speech emotion recognition (1) dysarthric speech recognition (1) voice cloning (1) zero-shot text-to-speech (1) codec encoder (1) self-pinching gate (1) emotion descriptor (1) model compression (1) emotion explainability (1) multi-task learning (1) information bottleneck (1)

Papers

Defending Unauthorized Voice Cloning with Watermark-Aware Codecs Interspeech 2025 Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Interspeech 2025 MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition Interspeech 2025 On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Interspeech 2025 Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition Interspeech 2025