verderey Goto Github PK

3d-convolutional-speaker-recognition

:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

bob.db.voxforge

Voxforge Database Access API for Bob used for Speaker Recognition

capstone-project

capstone-project-ibm

classification_attemption

Classification Test With Adaboost, ANN and etc.

coursera_capstone

Capstone project for the Coursera IBM Data Science Specialization

ctc-lstm

Theano implementation of CTC. Applied on TIMIT and a Toy dataset.

danet-tensorflow

Tensorflow implementation of "Speaker-independent Speech Separation with Deep Attractor Network"

das

Deep Adaptive Separator - DAS - Deep Learning architecture for Multi Speaker Separation

deep-belief-network

A Python implementation of Deep Belief Networks built upon NumPy and TensorFlow with scikit-learn compatibility

deep-speaker

Deep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/pdf/1705.02304.pdf

deepnet

Implementation of some deep learning algorithms.

dlg-segmenter

Recurrent Neural Networks for Speaker and Turn Taking Classification

dnnmapper

Mapping features using Deep Neural Networks (DNNs) with application to Voice Conversion (VC). The implementations are on top of Theano Python library

domain-adversarial-speaker-recognition-in-tensorflow

github-repository

graduation-project

Text-Independent Speaker Recognition Using Gaussian Mixture Models

ibm-cpp-week5

keras_extensions

A collection of small extensions to Keras (RBM, momentum schedule, ..)

nnets

Python neural network library

python_speech_features

This library provides common speech features for ASR including MFCCs and filterbank energies.

rbm-ae-tf

Tensorflow implementation of Restricted Boltzman Machine(RBM) and Autoencoder with layerwise pretraining.

samplernn_iclr2017

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

speaker-identification

A program for automatic speaker identification using deep learning techniques.

speaker-recognition

Final project for the course ECE446 - Sensory Communication at University of Toronto. The project is consisted of a Speaker Recognition system that uses Gaussian Mixture Models (GMM)

speaker-recognition-nn

Speaker Recognition application using fast-forward NN

speakerrecognition

Identify speakers from a sample of their speech.

theanodbn

Theano Deep Belief Network code extension.

timit_tools

tools around preparing TIMIT for HMM (with HTK) and deep learning (with Theano) methods

tts-dnn-models

multi-speaker TTS architecture based on DNNs using Python and Theano - Master's Thesis