Voice Recognition with RNN Neural Networks

Variational Bayes HMM over x-vectors diarization

feature extraction from speech signals

Tracking the progress in end-to-end speech translation

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

End-to-End Speech Processing Toolkit

Language modeling, LSTM, Attention models, Transformers, Parsing and Tagging in NLP, EM algorithm, Auto-encoders implemented in Python using PyTorch. The assignments are part of the course Natural …

PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech Recognition" (NeurIPS 2022)

Large, modern dataset for speech recognition

FSA/FST algorithms, differentiable, with PyTorch compatibility.

AMMI Speech Recognition project for low-resource language(Arabic)

This is the implementation of our Interspeech 2020 paper "Converting anyone's emotion: towards speaker-independent emotional voice conversion".

Speech synthesis using LPC

This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.

TTS Tensorflow description with the different models

Official implementation of Dynamical VAEs

A code for transliterating (romanizing) Arabic text using the American Library Association - Library of Congress (ALA-LC) standard

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

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 a…

🎯 Speech Recognition Challenge by Speech Lab - IIT Madras

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

Arabic speech recognition, classification and text-to-speech.

This project is to provide spell check help from Urdu to Hindi transliteration.The spelling errors in our case mostly comprises of errors in matras.

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

Latex code for making neural networks diagrams

automatically determine the intensity of emotions (E) and intensity of sentiment (aka valence V) of the tweeters from their tweets

Demo of how to visualize speech signals and analyze them