Code samples for my book "Neural Networks and Deep Learning"

This repository contains code to replicate results from the ICASSP 2020 paper "StarGAN for Emotional Speech Conversion: Validated by Data Augmentation of End-to-End Emotion Recognition".

Voice Converter Using CycleGAN and Non-Parallel Data

This is the GitHub page for publicly available emotional speech data.

As humans, interacting with people through speech is one of the most natural ways to express ourselves. We rely so much on our emotions that we don’t even realise that for most humans non verbal cu…

Emotions are important part of understanding human interactions. Research is going into finding methods that can at the very least mimic human ability to recognise emotions displayed in the form of…

While tightening and expansion of our facial muscles cause some changes called facial expressions as a reaction to the different kinds of emotional situations of our brain, similarly there are some…

Speech emotion recognition is a technology that extracts emotion features from computer speech signals, Compares them, and analyzes the feature parameters and the obtained emotion changes.

Speech Emotion Recognition is a technology that extracts emotion features from computer speech signals, compares them, and analyzes the feature parameters and the obtained emotion changes.

Speech Emotion recognition is a technology that extracts emotion feature from computer speech signals, compares them, and analysis the feature parameters and obtained emotion changes.

Here I have created a deep learning system that is capable of capturing the slight changes in human speech and based on that it determines what emotions have been conveyed through the speech.

Emotion Detecting and a small application to change the emotion.

Voice Warping with Emotion Change

When you are listening to music and the music player automatically plays songs matching to your emotions. This is one of the many use cases of Emotion detection using speech. Our main goal is to co…

Prosodt TTS acceconversion Modified Wav2vec to have 10ms shift and No vocoder available

Official implementation for the paper: A Unified One-Shot Prosody and Speaker Conversion System with Self-Supervised Discrete Speech Units.

Emotion Conversion by Prosody Modification Using Highway Net and Maximum Likelihood Objective

Prosody Modification for Neutral to Angry Speech Conversion project provides a comprehensive framework for transforming neutral speech into an angry-sounding version. By employing signal processing…

This project intends to develop a high-quality many-to-many emotion conversion model that can convert a speech audio into specified emotions. To achieve this goal, we use pretrained parallel CNN-tr…

Expressive Voice Conversion

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

Speech to text conversion(vice-versa),E-mail voice assistance,Emotion detection,Song recommender using facial detection,Video search through voice assistance,audio to text,Sign languaguage to text.

Voice Vibes was made by me with the help of my trainer. I used Jupyter Notebook to create the code. Voice Vibes has 3 parts to it. The first is emotion recognition, recognizing the sentence given a…

This is the official implement of A Controllable Emotion Voice Conversion Framework with Pre-trained Speech Representations

Novel VAE-based Framework to Infer Complex Speaking Style from Arbitrary Speaker and Emotion State

Voice emotion conversion model for DS/ML master's thesis. F0 contour mapping in sequence-to-sequence RNN-LSTM architecture in Tensorflow.

This is the demo page of the paper "Emotional Voice Conversion: Theory, Databases, and ESD"

Audio samples for Nonparallel Emotional Voice Conversion for unseen speaker-emotion combination using dual domain classifiers and virtual domain mixing training