librosa

Sound-Classification-Short-Time-Fourier-Transform-STFT

RealCatTranslator

Project in several phases to ultimately built an app that translate from human to cats and cats to human using deep learning algorithm

dtw-app

app to align midi with audio: step 1 - apply dynamic time warp algorithm, step 2 - manually adjust inconsistencies

speech-emotion-recognition

A program that uses neural networks to detect emotions from pre-recorded and real-time speech

Audio-Scene-Classification

Scene Classification using Audio in the nearby Environment.

DSP-Project

Digital Signal Processing mini project: Autotune

Bird-Song-Classification

Classify bird species based on their songs using SIamese Networks and 1D dilated convolutions.

audio-peak-detection

Python script utilising Librosa to log the timings of audio peaks in an MP3 file

heartbeat-sounds

Heart Sound Segmentation And Classification | Kaggle Competition

infinity-player

infinite jukebox clone using librosa

MusicGenreClassification

Music Genre Classification with all data pipeline steps

Virtual-Psychiatrist

This is an app which helps a user to deal with depression at a basic level by providing them Cognitive - Behavioral Therapy i.e. CBT Therapy in order to overcome various psychological problems and guide them to go take assistance by visiting an actual Psychologist.

lung-sound-classification

Diagnosing respiratory diseases using sounds of respiratory cycles.

speech-to-text

Speaker diarization and speech to text

audio-embedding

Extract audio embeddings from an audio file using Python

Audio-Signal-Processing-and-Feature-Extraction

Feature extraction from audio signal (explained in Persian)

gunshot-detection-system

This repository contains the Python code for a audio classification system designed to detect gunshots in urban settings.

HipHopPopularity

Building a predictive model for the popularity of an unreleased hip hop track on Spotify

Conditional-SpecGAN-Tensorflow

Text-to-Speech Synthesis by Generating Spectrograms using Generative Adversarial Network

librosapp

A C++ implementation of stft, melspectrogram and mel_to_stft

voice-converter

Module for freely modifying or controlling voice

WildWav

Bird sound identification web application

data

Example (audio) data for use with librosa

Sound-Recognition

Bird's tweet classification with Deep Learning

RespireNet-Respiratory-Disease-Prediction-Web-Application-Using-Deep-Learning

RespireNet is an innovative web-based application that harnesses the capabilities of deep learning and Mel-frequency cepstral coefficients (MFCC) as a feature extraction technique for accurate respiratory disease prediction. The primary objective of this user-friendly web application is to facilitate early detection.

COVID-19-Detection-From-Speech-Using-Deep-Learning

This repository contains project COVID-19 Detection from Speech. There are 4 coding files with 4 different strategies.

Speech_Emotion_Recognition_Model

A speech emotion detection classifier on CREMA dataset. This classifier attempts to recognize human emotion and effective states from speech.

Music-Instrument-Recognition

A Convolutional Neural Network and a K nearest neighbour based classifier to detect the musical instrument present in a given audio file. It can be used for monophonic files. Both classifiers performed well with accuracy above 90%

Exploratory_Data_Analysis_and_ML_Projects

Several datasets are manipulated, visualized, and analyzed with well-known ML Algorithms to make predictions, clustering, or classifications.

manhuw

Recognizing and identifying Quran reciters from audio recordings.

Speech-Emotion-Recognition-in-Tensorflow-Using-CNNs

Speech Emotion Recognition (SER) using CNNs and CRNNs Based on Mel Spectrograms and Mel Frequency Cepstral Coefficients (MFCCs)

Deep-Learning-and-Digital-Signal-Processing-for-Environmental-Sound-Classification

Automatic environmental sound classification (ESC) based on ESC-50 dataset (and ESC-10 subset)

capstone-2022-15

IN4U - 면접 연습 웹 서비스

SPEECH-TO-EMOTION

Emotion is an intuitive feeling which can be determined from any person’s circumstances and surroundings. But in this project, we tried to identify the emotional state of a person using his voice as input.

Audio-Classification-using-Deep-Neural-Nets

Building a High-End Audio Classification System using Deep Neural Nets and Librosa