27 citations · 43 across the 9 of their papers we have counts for
9 papers
AudioMorphix: Training-free audio editing with diffusion probabilistic models
Jinhua Liang, Yuanzhe Chen, Yi Yuan +5
Editing sound with precision is a crucial yet underexplored challenge in audio content creation. While existing works can manipulate sounds by text instructions or audio exemplar p…
Mind the Domain Gap: a Systematic Analysis on Bioacoustic Sound Event Detection
Jinhua Liang, Ines Nolasco, Burooj Ghani +3
Detecting the presence of animal vocalisations in nature is essential to study animal populations and their behaviors. A recent development in the field is the introduction of the…
WavCraft: Audio Editing and Generation with Large Language Models
Jinhua Liang, Huan Zhang, Haohe Liu +7
We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically,…
Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
Jinhua Liang, Xubo Liu, Wenwu Wang +3
The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) hav…
WavJourney: Compositional Audio Creation with Large Language Models
Xubo Liu, Zhongkai Zhu, Haohe Liu +8
Despite breakthroughs in audio generation models, their capabilities are often confined to domain-specific conditions such as speech transcriptions and audio captions. However, rea…
Adapting Language-Audio Models as Few-Shot Audio Learners
Jinhua Liang, Xubo Liu, Haohe Liu +4
We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we…
Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study
Yi Yuan, Haohe Liu, Jinhua Liang +3
Deep neural networks have recently achieved breakthroughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale da…
Learning from Taxonomy: Multi-label Few-Shot Classification for Everyday Sound Recognition
Jinhua Liang, Huy Phan, Emmanouil Benetos
Everyday sound recognition aims to infer types of sound events in audio streams. While many works succeeded in training models with high performance in a fully-supervised manner, t…
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture
Jinhua Liang, Tao Zhang, Guoqing Feng
Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural n…