End-2-end speech synthesis with recurrent neural networks

Front-end speech processing aims at extracting proper features from short- term segments of a speech utterance, known as frames. It is a pre-requisite step toward any pattern recognition problem employing speech or audio (e.g., music). Here, we are interesting in voice disorder classification. That is, to develop two-class classifiers, which can discriminate between utterances of a subject suffering from say vocal fold paralysis and utterances of a healthy subject.The mathematical modeling of the speech production system in humans suggests that an all-pole system function is justified [1-3]. As a consequence, linear prediction coefficients (LPCs) constitute a first choice for modeling the magnitute of the short-term spectrum of speech. LPC-derived cepstral coefficients are guaranteed to discriminate between the system (e.g., vocal tract) contribution and that of the excitation. Taking into account the characteristics of the human ear, the mel-frequency cepstral coefficients (MFCCs) emerged as descriptive features of the speech spectral envelope. Similarly to MFCCs, the perceptual linear prediction coefficients (PLPs) could also be derived. The aforementioned sort of speaking tradi- tional features will be tested against agnostic-features extracted by convolu- tive neural networks (CNNs) (e.g., auto-encoders) [4]. The pattern recognition step will be based on Gaussian Mixture Model based classifiers,K-nearest neighbor classifiers, Bayes classifiers, as well as Deep Neural Networks. The Massachussets Eye and Ear Infirmary Dataset (MEEI-Dataset) [5] will be exploited. At the application level, a library for feature extraction and classification in Python will be developed. Credible publicly available resources will be 1used toward achieving our goal, such as KALDI. Comparisons will be made against [6-8].

This project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.

用Tensorflow实现的深度神经网络。

Deep learning approach for estimation of Remaining Useful Life (RUL) of an engine

Stringlifier is on Opensource ML Library for detecting random strings in raw text. It can be used in sanitising logs, detecting accidentally exposed credentials and as a pre-processing step in unsupervised ML-based analysis of application text data.

Character Embeddings Recurrent Neural Network Text Generation Models

A tensorflow implementation for EEGLearn

Source Code Generation Based On User Intention Using LSTM Networks

If you've always wanted to learn about deep-learning but don't know where to start, then you might have stumbled upon the right place!

Time-series prediction with LSTNet in Apache MXNet Gluon

Large-scale Exploration of Neural Relation Classification Architectures

Real-time, Multi-person & Multi-camera Fall Detector in Python

Statistical Analysis on E-Commerce Reviews, with Sentiment Classification using Bidirectional Recurrent Neural Network (RNN)

A simple LSTM network to predict bitcoin closing prices

Image classification using CNN

Hybrid biLSTM and CNN architecture for Sentence Unit Detection

Named Entity Recognition - Python - Keras

This is a practical implementation implementing neural networks on top of fasttext as well as word2vec word embeddings.

The repository contains all the code for the paper amino acid encoding using deep learning application

Sentiment Analysis using Recurrent Neural Networks (RNN-LSTM) and Google News Word2Vec

Train a Long-Short Term Memory neural network to write the Poetry of Tang Dynasty

LSTM Sentiment Analysis

Hippocampus spike activity related to the depression-related behaviors after stress. Propose the stress determinator

My Projects Submission to Udacity's Deep Learning Nanodegree Program

Fake News Detection Using Recurrent Neural Networks (RNNs) & Long Short Term Memory (LSTM).

It analyses the movie review entered by a user for any specific movie and analyses what is the sentiment of the review. It helps the companies rate the movie and understand crowd sentiment regarding it. Sentiment analysis is a natural language processing problem where text is understood and the underlying intent is predicted.

Using high-level frameworks like Keras, TensorFlow or PyTorch allows us to build very complex models quickly. However, it is worth taking the time to look inside and understand underlying concepts. Not so long ago I published an article, explaining — in a simple way — how neural nets work. However, it was a highly theoretical post, dedicated primarily to math, which is the source of the NN superpower. From the beginning, I was planning to follow-up on this topic in a more practical way. This time we will try to utilize our knowledge and build a fully operational neural network using only NumPy.

Leverage the power of Keras to build and train state-of-the-art deep learning models