zky-66

pytorch-self-distillation-final

sound_event_detection_transformer

code for sound event detection transformer (SEDT) and self-supervised pre-training SEDT (SP-SEDT)

sound_event_detection_dcase2017_task4

SSDPT

Codes for SSDPT: Self-Supervised Dual-Path Transformer for Anomalous Sound Detection

VAED_HeterGraph

The implementation for Interspeech22 "Visually-aware Acoustic Event Detection using Heterogeneous Graphs" paper

cinc2022

Heart Murmur Detection from Phonocardiogram Recordings: The George B. Moody PhysioNet Challenge 2022

heart-murmur-detection

Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection (Physionet Challenge 2022)

python-classifier-2022

Python example classifier for the PhysioNet Challenge 2022

STgram-MFN

A spectro-temporal fusion feature, STgram, with MobileFaceNet For more stable Anomalous Sound Detection

TUNet

DNS-Challenge

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

CleanUNet

Official PyTorch Implementation of CleanUNet (ICASSP 2022)

bwe_historical_recordings

Bandwidth Extension of Historical Recordings using Generative Adversarial Networks

Pengi

An Audio Language model for Audio Tasks

audio-dataset

Audio Dataset for training CLAP and other models

AudioCLIP

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

CLAP

Contrastive Language-Audio Pretraining

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.

byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

psla

Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".

vocalsound

Dataset and baseline code for the VocalSound dataset (ICASSP2022).

clap_curation

DCASE_2022_Task_5

System that ranks 2nd in DCASE 2022 Challenge Task 5: Few-shot Bioacoustic Event Detection

CLAP

Learning audio concepts from natural language supervision

EfficientAT

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

SimPFs

Code for "Simple Pooling Front-ends for Efficient Audio Calssification", ICASSP 2023

FCAC

Few-shot class-incremental audio classification, which can continually recognize novel audio classes without forgetting old ones

channel-attention

Gluon implementation of channel-attention modules: SE, ECA, GCT

FDY-SED