timit · GitHub Topics

#计算机科学#pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are ...

翻译 - pytorch-kaldi是一个用于开发最先进的DNN / RNN混合语音识别系统的项目。 DNN部分由pytorch管理，而特征提取，标签计算和解码则通过kaldi工具箱执行。

speech-recognition gru dnn kaldi rnn-model PyTorch timit 深度学习深度神经网络 recurrent-neural-networks multilayer-perceptron-network lstm speech asr rnn

Python 2.38 k

3 年前

mravanelli / SincNet

#计算机科学#SincNet is a neural architecture for efficiently processing raw audio samples.

深度学习 audio waveform filtering cnn convolutional-neural-networks speaker-recognition speaker-verification speech-recognition asr audio-processing speech-processing digital-signal-processing signal-processing neural-networks 人工智能 timit PyTorch Python

Python 1.16 k

4 年前

speechbrain / speechbrain.github.io

#计算机科学#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 a...

深度学习 speech-recognition speech-to-text speech speech-processing speaker-recognition speaker-verification speech-separation speechrecognition 神经网络 neural-networks timit speech-analysis

HTML 366

3 个月前

hirofumi0810 / tensorflow_end2end_speech_recognition

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

speech-recognition ctc Tensorflow timit timit-dataset attention-mechanism automatic-speech-recognition asr end-to-end end-to-end-learning speech-to-text beam-search

Python 315

7 年前

philipperemy / timit

The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus.

timit-dataset timit darpa speech

299

3 年前

Diamondfan / CTC_pytorch

CTC end -to-end ASR for timit and 863 corpus.

ctc PyTorch timit kaldi decoder

Python 217

5 年前

HawkAaron / RNN-Transducer

MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks

end-to-end asr transducers mxnet rnn-transducer timit speech-recognition

Python 138

4 年前

WindQAQ / listen-attend-and-spell

Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API of Tensorflow, which makes the training and evaluation truly en...

speech-recognition Tensorflow timit seq2seq speech-to-text

Python 89

6 年前

grausof / keras-sincnet

#计算机科学#Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

深度学习 audio waveform filtering cnn convolutional-neural-networks speaker-recognition speaker-verification speech-recognition asr audio-processing speech-processing digital-signal-processing 神经网络机器学习人工智能 timit Tensorflow Keras

Python 72

4 年前

hirofumi0810 / asr_preprocessing

Python implementation of pre-processing for End-to-End speech recognition

speech-recognition ctc attention-mechanism timit timit-dataset automatic-speech-recognition end-to-end transcription preprocessing dataset

Python 69

7 年前

matthijsvk / TIMITspeech

Speech recognition on the TIMIT (or any other) dataset

speech timit 神经网络 theano phonemes speech-recognition

Python 42

7 年前

mravanelli / pytorch_MLP_for_ASR

#计算机科学#This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation sup...

PyTorch asr kaldi 深度学习深度神经网络 speech-recognition timit mlp feedforward-neural-network multilayer-perceptron neural-networks Python CUDA

Perl 38

7 年前

AppleHolic / PytorchSR

Pytorch based phoneme recognition (TIMIT phoneme classification)

PyTorch Bukkit timit speechrecognition

Python 34

7 年前

mravanelli / theano-kaldi-rnn

#计算机科学#THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.

recurrent-neural-networks kaldi rnn gru timit theano 深度学习深度神经网络

Perl 33

7 年前

zhaoyu611 / Automatic_Speech_Recognition_with_Multi_Models

#计算机科学#A Simple Automatic Speech Recognition (ASR) Model in Tensorflow, which only needs to focus on Deep Neural Network. It's easy to test popular cells (most are LSTM and its variants) and models (unidirec...

automatic-speech-recognition Tensorflow ctc lstm 深度学习 timit rnn

Python 19

7 年前