My Docker scripts and Dockerfile for several frameworks.

Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.

The Hidden Markov Model Toolkit (HTK) from University of Cambridge, with fixed issues.

HTK Toolkit with Linux 64 bit and Docker support

Automatic speech recognition (ASR) for Indonesian language built by using HTK and Julius. Web interface is built using Node.js.

Browser for long audio recordings.

Installation steps of HTK 3.5 under Ubuntu

P2FA-based HMM state-level forced aligner

Speech Tester is a set of Python scripts conceived as an extension to HTK Automatic Speech Recognition system (Young et al., 2002). Speech Tester aims to help language researchers and engineers to measure the intelligibility of transformed audio signals. Here the termed “transform” may describe any process that alters a speech signal or its rece…

Minimal HTK for supporting HTK in Vietnamese.

Wrist Wash Gesture Recognition

Python wrapper for the Cambridge Hidden Markov Model Toolkit

Scripts para treino de modelos acústicos

Offer hwyluso creu Adnabod Lleferydd Cymraeg gyda HTK, IRSTLM, Julius a Docker | Welsh Speech Recognition with HTK, IRSTLM, Julius and Docker

Digital Signal Processing: HMM Training and Testing with the HTK toolkit

86.53 - Algorithms used in speech recognition and application use of the HTK toolkit for a speech recognition system to make phone calls with voice.

This project focuses on building a speech recognition system for the Farsi (Persian) language using Hidden Markov Models (HMMs) and the HTK (Hidden Markov Model Toolkit) library. The goal is to recognize spoken digits (1, 2, 4, and 8) through the implemented HMM model.

Gesture Recognition using HMMs

Course assignments for LS621 (IIT Guwahati, Jan-May 2018)