Mirco Ravanelli

wav2aug. A general purpose task-agnostic speech augmentation policy

speechbrain. A PyTorch-based Speech Toolkit

open-speech-corpora. 💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

benchmarks. This repository contains the SpeechBrain Benchmarks

Speech. 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)

eeg-pytorch-bci. This repository provides a comprehensive pipeline for analyzing motor imagery EEG data using MNE-Python and PyTorch.

moabb. Mother of All BCI Benchmarks

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

orion. Asynchronous Distributed Hyperparameter Optimization.

voice2json. Command-line tools for speech and intent recognition on Linux

torchdrug. A powerful and flexible machine learning platform for drug discovery

common-voice. Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

speechbrain.github.io. The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.

s3prl. Self-Supervised Speech Pre-training and Representation Learning Toolkit

voxpopuli. A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

HyperPyYAML. Extensions to YAML syntax for better python interaction

BIRD. Big Impulse Response Dataset

babyai. BabyAI platform. A testbed for training agents to understand and execute language commands.

pase. Problem Agnostic Speech Encoder

quantum_training. Repository of QC Experiments based on D-Wave Leap

end-to-end-SLU. PyTorch code for end-to-end spoken language understanding (SLU) with ASR-based transfer learning

welcome_tutorials. Various tutorials given for welcoming new students at MILA.

python_speech_features. This library provides common speech features for ASR including MFCCs and filterbank energies.

DIRHA_English_wsj. Tools and kaldi baselines for the DIRHA English wsj dataset

pytorch-kaldi. pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

twinnet-asr. Implementation of speech recognition with TwinNet

irasl2018. Code for the paper "Investigating the effect of residual and highway connections in speech enhancement models"

kaldi-io-for-python. Python functions for reading kaldi data formats. Useful for rapid prototyping with python.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

Quaternion-Recurrent-Neural-Networks. This is the code for the paper 'Quaternion Recurrent Neural Networks'.

SincNet. SincNet is a neural architecture for efficiently processing raw audio samples.

kaldi. kaldi-asr/kaldi is the official location of the Kaldi project.

GAN. Tutorial on GANs

pytorch_MLP_for_ASR. This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided.

pySpeechRev. This python code performs an efficient speech reverberation starting from a dataset of close-talking speech signals and a collection of acoustic impulse responses.

pydrobert-kaldi. SWIG bindings for Kaldi I/O, built with Conda

theano-kaldi-rnn. THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.