7 papers · 1 filter
LiteCASS: A Lightweight End-to-End Network for Real-Time Stereo Cinematic Audio Source Separation
Yuanxin Guo, Qiang Ji, Mengmei Liu +3
Cinematic audio source separation (CASS) decomposes a soundtrack into dialogue, music, and sound-effects (SFX) stems. Existing CASS methods, however, suffer from two critical limit…
Grounded Decoding for Autoregressive Speech Enhancement via Adaptive Code-Space Grounding and Local LLM Refinement
Hao Shi, Yuan Gao, Zhaoheng Ni +4
Large language model (LLM)-based autoregressive speech enhancement (SE) produces natural speech using learned clean-speech priors, but may hallucinate content unsupported by the in…
A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification
Beile Ning, Jiayi Yu, Zitong Wang +5
This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to the Broad Sound Taxonomy (BST)…
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
Hongyu Jin, Siyi Wang, Yang Xiao +11
Humans process rich auditory environments through various cognitive capabilities such as audio perception, audio reasoning and memory. Despite recent progress in large audio-langua…
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
Siyi Wang, Shihong Tan, Siyi Liu +4
Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In cont…
A Unified Neural Codec Language Model for Selective Editable Text to Speech Generation
Hanchen Pei, Shujie Liu, Yanqing Liu +5
Neural codec language models achieve impressive zero-shot Text-to-Speech (TTS) by fully imitating the acoustic characteristics of a short speech prompt, including timbre, prosody,…
Online neural fusion of distortionless differential beamformers for robust speech enhancement
Yuanhang Qian, Kunlong Zhao, Jilu Jin +4
Fixed beamforming is widely used in practice since it does not depend on the estimation of noise statistics and provides relatively stable performance. However, a single beamformer…