Data simulation scripts for paper "Target Sound Extraction with Variable Cross-modality Clues"

The implementation of "X-TF-GridNet: A Time-Frequency Domain Target Speaker Extraction Network with Adaptive Speaker Embedding Fusion", which is accepted by Information Fusion.

Music repair method to convert lossy MP3 compressed music to lossless music.

The pytorch implementation of BERP: A Blind Estimator of Room acoustic and physical Parameters

torch-optimizer -- collection of optimizers for Pytorch

Ambisonic Blind Reverberation Time Estimation

ESC-50: Dataset for Environmental Sound Classification

Mamba SSM architecture

Neural IIR Filter Field for HRTF Upsampling and Personalization

Deep network that performs spectral clustering

Real-time GCC-NMF Blind Speech Separation and Enhancement

Co-Separating Sounds of Visual Objects (ICCV 2019)

Sound event localization, detection, and tracking of multiple overlapping and moving sources in 2D spherical space using convolutional recurrent neural network

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)

A deep neural network architecture for low-latency audio processing

Full implementation of "End-to-end microphone permutation and number invariant multi-channel speech separation" (Interspeech 2020)

An unofficial PyTorch implementation of Music Source Separation with Band-split RNN for MDX-23 ("Label Noise" Track)

Perceptual Quality Estimator for speech and audio

Selective Hearing: A Machine Listening Perspective

Python implementation of the Short Term Objective Intelligibility measure

Tools for Speech Enhancement integrated with Kaldi

Speech Localization and Separation using DNNs

[NeurIPS 2020] Official repository for the project "Listening to Sound of Silence for Speech Denoising"

an extremely simple tool for separating vocals and background music, completely localized for web operation, using 2stems/4stems/5stems models 这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网