6 papers · 1 filter
VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics
Zhikang Niu, Wenming Tu, Yalin Li +8
Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key li…
Route-DMD: Distribution Matching Distillation with Task-Routed Mechanism for Speech Foundation Models
Yanru Huo, Zhikang Niu, Wenming Tu +7
Speech foundation models built on flow matching handle generation, editing, and processing in one system, but every request costs 20-50 iterative steps, and classifier-free guidanc…
TinyAudio: Compact and Efficient Text-to-Audio Generation for Low-Resource Deployment
Junxi Liu, Xiquan Li, Wenhao Guan +5
Text-to-audio (TTA) generation has advanced rapidly in generation quality and instruction following. However, representative systems often require around a billion parameters, limi…
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
Ziyang Ma, Zhikang Niu, Wenming Tu +30
We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To sup…
MMAE: A Massive Multitask Audio Editing Benchmark
Ziyang Ma, Ruiqi Yan, Ruiyang Xu +35
We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.…
DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration
Yanru Huo, Ziyue Jiang, Zuoli Tang +2
While Diffusion Transformers (DiT) have advanced non-autoregressive (NAR) speech synthesis, their high computational demands remain an limitation. Existing DiT-based text-to-speech…