Our lab is committed to cutting-edge research in speech generation, spoken dialogue systems, and spatial audio generation. We strive to develop intelligent, natural, and immersive audio technologies that advance human–machine interaction and multimedia experiences.
MM-Speech
Popular repositories Loading
-
DiTReducio
DiTReducio Public[ACL 2026] DiTReducio: A Training-Free Acceleration for DiT-Based TTS viaProgressive Calibration
-
DualAxisRM
DualAxisRM Public[ACL 2026] Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models
Python 12
-
SwanBench-Speech
SwanBench-Speech Public[ACL 2026] SwanBench-Speech: Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios
-
SDiaReward
SDiaReward Public[ACL 2026] SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
Repositories
Showing 10 of 12 repositories
- SDiaReward Public
[ACL 2026] SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
MM-Speech/SDiaReward’s past year of commit activity - SwanSphere Public
[ICML 2026] Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
MM-Speech/SwanSphere’s past year of commit activity - DualAxisRM Public
[ACL 2026] Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models
MM-Speech/DualAxisRM’s past year of commit activity - TMD-Bench Public
[ICML 2026] TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation
MM-Speech/TMD-Bench’s past year of commit activity - EMO-TTS Public
[ACL 2026] Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech
MM-Speech/EMO-TTS’s past year of commit activity - DiTReducio Public
[ACL 2026] DiTReducio: A Training-Free Acceleration for DiT-Based TTS viaProgressive Calibration
MM-Speech/DiTReducio’s past year of commit activity - WavAlign Public
[ACL 2026] WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training
MM-Speech/WavAlign’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…