Kaidi Wang

5 papers · 2024–2025 · 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 · Bronze 🗺️ Taxonomy Completionist (12)

Venues

Interspeech (5)

Top co-authors

Qingyang Hong (5) Lin Li (5) Wenhao Guan (4) Hukai Huang (3) Peijie Chen (3) Weijie Wu (2) Ziyue Jiang (1) Shenghui Lu (1) Yang Wang (1) Jinanglong Yao (1)

Research topics

Deep Learning (5) Speech & Audio (4) Learning Types (4) Synthesis (3) Architectures (2) Models (2) Artificial Intelligence (1) Core AI (1) Processing (1)

Keywords

flow matching (2) voice conversion (2) disentangled representation (1) codebook learning (1) ordinary differential equation (1) latent diffusion model (1) rectified flow (1) text-to-audio generation (1) audio synthesis (1) single-channel speech enhancement (1) speech reconstruction (1) prosody control (1) speech codec (1) sub-band processing (1) continuous normalization flow (1) deep filtering (1) time-frequency bin (1) dual-stage training (1) convolutional feature extraction (1) in-context learning (1)

Papers

A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement Interspeech 2025 Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion Interspeech 2025 DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec Interspeech 2025 ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization Interspeech 2025 LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation Interspeech 2024