Adapting Language-Audio Models as Few-Shot Audio Learners
This paper gets accepted by INTERSPEECH 2023.
Posts by Tag
- audio classification 4
- acoustic scene classification 3
- few-shot learning 3
- large language model 2
- model compression and acceleration 1
- acoustic understanding 1
- self-supervised learning 1
- audio tagging 1
- cross-modality learning 1
- audio understanding 1
- AI agent 1
- audio generation and editing 1
- bioacoustic classification 1
audio classification
Learning from Taxonomy: Multi-label Few-shot Classification for Everyday Sound Recognition
This paper is accepted by ICASSP2024.
Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture
This paper is accepted by IEEE Access.
Research on efficient acoustic scene recognition based on deep learning
The goal is to explore high-performance acoustic scene classification (ASC) technologies at a low computational cost.
acoustic scene classification
Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture
This paper is accepted by IEEE Access.
Research on efficient acoustic scene recognition based on deep learning
The goal is to explore high-performance acoustic scene classification (ASC) technologies at a low computational cost.
Acoustic scene classification using deep cnn with fine-resolution feature
Accepted by Expert Systems with Applications.
few-shot learning
Mind the Domain Gap: a Systematic Analysis on Bioacoustic Sound Event Detection
This paper gets accepted by EUSIPCO 2025.
Learning from Taxonomy: Multi-label Few-shot Classification for Everyday Sound Recognition
This paper is accepted by ICASSP2024.
[Project launch] Everyday sound recognition with limited annotations
The goal is to explore general-proposed audio understanding in the limited annotations.
large language model
WavCraft: Audio Editing and Generation with Large Language Models
This paper gets accepted by ICLR workshop on LLM agent.
Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
This paper is under peer review.
model compression and acceleration
Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture
This paper is accepted by IEEE Access.
acoustic understanding
[Project launch] Everyday sound recognition with limited annotations
The goal is to explore general-proposed audio understanding in the limited annotations.
self-supervised learning
[Project launch] Everyday sound recognition with limited annotations
The goal is to explore general-proposed audio understanding in the limited annotations.
audio tagging
Learning from Taxonomy: Multi-label Few-shot Classification for Everyday Sound Recognition
This paper is accepted by ICASSP2024.
cross-modality learning
Adapting Language-Audio Models as Few-Shot Audio Learners
This paper gets accepted by INTERSPEECH 2023.
audio understanding
Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
This paper is under peer review.
AI agent
WavCraft: Audio Editing and Generation with Large Language Models
This paper gets accepted by ICLR workshop on LLM agent.
audio generation and editing
WavCraft: Audio Editing and Generation with Large Language Models
This paper gets accepted by ICLR workshop on LLM agent.
bioacoustic classification
Mind the Domain Gap: a Systematic Analysis on Bioacoustic Sound Event Detection
This paper gets accepted by EUSIPCO 2025.