Audio Source Separation on steroids

Data manipulation and transformation for audio signal processing, powered by PyTorch

This is the repo storing the new rttm reference generated from forced-alignment for CHiME-6 challenge.

Deep learning based Speech Beamforming

Domestic environment sound event detection task

Single channel speech source separation by diffusion process (ICASSP 2023)

End-to-End Speech Processing Toolkit

A simple package for Guided source separation (GSS)

High performance implementation of Extreme Learning Machines (fast randomized neural networks).

Training data simulation

This is the official location of the Kaldi project.

Dual Path Networks for Keras 2.0+

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

NOTSOFAR-1 Challenge: Distant Diarization and ASR

Code to simulate a reverberated, noisy version of the WSJ-2MIX dataset