Lists (9)
Stars
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
The official repo of UL-UNAS, an ultra-lightweight SE model.
Encode and decode audio samples to/from continuous and discrete compressed representations!
A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.
A unified evaluation suite for speech-to-text translation, covering SpeechLLMs, SFMs, and cascaded systems across diverse real-world speech phenomena.
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…
A Conversational Speech Generation Model
Keep track of big models in audio domain, including speech, singing, music etc.
Style transfer of synthetic electric guitar to more realistic electric guitar audio using flow matching.
An implementation of the Sottek Hearing Model psychoacoustic sound quality metrics defined in ECMA-418-2.
An enhanced version of All-In-One with integrated source separation and modern PyTorch compatibility
Compute distribution-based quality metrics for audio data using embeddings, with a focus on music.
Official repository for the paper "MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement" (Accepted to IEEE Transactions on Audio, Speech, and Language …
Speed-optimized streaming neural speech enhancement network
A must-read paper for speech separation based on neural networks
Official implementation of the Sheet Music Transformer
Code of our ISMIR 2025 paper - D. Afchar, G. Meseguer Brocal, K. Akesbi, R. Hennequin
Fast linear discrete time filtering in PyTorch.
Official repository for the paper - SLAP: Siamese Language-Audio Pretraining without negative samples for Music Understanding
A deep learning model for dynamic range compression modeling. Accompanying repository of the DAFx 2025 paper "Empirical Results for Adjusting Truncated Backpropagation Through Time while Training N…
A Large Dataset of Paired Guitar Audio Recordings and Tablatures
(ICASSP 2025, official code)FlowSE: Flow Matching-based Speech Enhancement