3 papers
eess.AS2026
VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track
Wenming Tu, Jian Gao, Yanru Huo +9
Audio reasoning requires multi-step, evidence-grounded inference over temporally dynamic and acoustically mixed signals, exceeding conventional perception tasks such as ASR or capt…
cs.SD2026
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.…
cs.SD2025
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…