speech-analysis

A high-quality speech analysis, manipulation and synthesis system

Praat: Doing Phonetics By Computer

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.

This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

feature extraction from speech signals

General Speech Restoration

My-Voice Analysis is a Python library for the analysis of voice (simultaneous speech, high entropy) without the need of a transcription. It breaks utterances and detects syllable boundaries, fundamental frequency contours, and formants.

A vocoder framework which had been widely used in research community since 1999.

Trained models for automatic speech recognition (ASR). A library to quickly build applications that require speech to text conversion.

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).

General Speech Restoration

A Python library for measuring the acoustic features of speech (simultaneous speech, high entropy) compared to ones of native speech.

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.

Script to calculate SNR and SDR using python

Localized Narratives

Pitch detection and pitch tracking, voicing unvoicing detection (VAD)，基音检测

Keras Implementation of Deepmind's WaveNet for Supervised Learning Tasks

MATLAB real-time/interactive speech tools. This series is obsolete. SP3ARK is the up-to-date series (will be).

SpeCT - Speech Corpus Toolkit for Praat. Documentation: https://lennes.github.io/spect/

Toolkit to asses speech impairments in patients with neurological disorders

Analytic signal-based source information analysis for YANGstraight and real-time interactive tools

An opensource harmonizer implementation leveraging the DISTRHO Plugin Framework.

Language data store and linguistic query API

Praaline is an open-source system to manage, annotate, visualise and analyse spoken language corpora

Automatic Speech Recognition

[wip]Speech recognition tool-box written by Nim. Based on Arraymancer.

Predicting emotions based on speech audio samples of American English, German and British English languages using Support Vector Machine, K-Nearest Neighbor, Random Forest and Recurrent Neural Network. Analyzing the performance of each model based on the dataset.

Many ASRs under one roof. With Benchmarking... answering the question. What is the best ASR?

In this project, the performance of speech emotion recognition is compared between two methods (SVM vs Bi-LSTM RNN).Conventional classifiers that uses machine learning algorithms has been used for decades in recognizing emotions from speech. However, in recent years, deep learning methods have taken the center stage and have gained popularity for their ability to perform well without any input hand-crafted features. Speech emotion on sets obtained from RAVDESS corpus is classified using a conventionally used Support Vector Machine (SVM) and its performance is compared to that of a bidirectional long short-term memory (LSTM).

A random forest classifier to predict the age-group and gender of a speaker from voice measurements.