InaspeechsegmenterCNN-based audio segmentation toolkit. Allows to detect speech, music and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
Stars: ✭ 352 (+1970.59%)
Mutual labels: speech, segmentation
TfvosSemi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.
Stars: ✭ 151 (+788.24%)
Mutual labels: recurrent-neural-networks, segmentation
Pytorch Kaldipytorch-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 performed with the kaldi toolkit.
Stars: ✭ 2,097 (+12235.29%)
Mutual labels: speech, recurrent-neural-networks
Awesome TensorlayerA curated list of dedicated resources and applications
Stars: ✭ 248 (+1358.82%)
Mutual labels: recurrent-neural-networks, segmentation
TF-Speech-Recognition-Challenge-SolutionSource code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.
Stars: ✭ 58 (+241.18%)
Mutual labels: speech, recurrent-neural-networks
D-TDNNPyTorch implementation of Densely Connected Time Delay Neural Network
Stars: ✭ 60 (+252.94%)
Mutual labels: speech
lung-image-analysisA basic framework for pulmonary nodule detection and characterization in CT
Stars: ✭ 26 (+52.94%)
Mutual labels: segmentation
datastories-semeval2017-task6Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (+17.65%)
Mutual labels: recurrent-neural-networks
kaldi helpers🙊 A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.
Stars: ✭ 13 (-23.53%)
Mutual labels: speech
entity-networkTensorflow implementation of "Tracking the World State with Recurrent Entity Networks" [https://arxiv.org/abs/1612.03969] by Henaff, Weston, Szlam, Bordes, and LeCun.
Stars: ✭ 58 (+241.18%)
Mutual labels: recurrent-neural-networks
VAD-LTSDEfficient voice activity detection algorithm using long-term speech information
Stars: ✭ 37 (+117.65%)
Mutual labels: speech
datasets🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Stars: ✭ 13,870 (+81488.24%)
Mutual labels: speech
deepspeech.mxnetA MXNet implementation of Baidu's DeepSpeech architecture
Stars: ✭ 82 (+382.35%)
Mutual labels: speech
Polygonization-by-Frame-Field-LearningThis repository contains the code for our fast polygonal building extraction from overhead images pipeline.
Stars: ✭ 161 (+847.06%)
Mutual labels: segmentation
deep-learningAssignmends done for Udacity's Deep Learning MOOC with Vincent Vanhoucke
Stars: ✭ 94 (+452.94%)
Mutual labels: recurrent-neural-networks
nicMSlesionsEasy multiple sclerosis white matter lesion segmentation using convolutional deep neural networks.
Stars: ✭ 33 (+94.12%)
Mutual labels: segmentation
wasr networkWaSR Segmentation Network for Unmanned Surface Vehicles v0.5
Stars: ✭ 32 (+88.24%)
Mutual labels: segmentation
JD-NMFJoint Dictionary Learning-based Non-Negative Matrix Factorization for Voice Conversion (TBME 2016)
Stars: ✭ 20 (+17.65%)
Mutual labels: speech
SpeakerDiarization RNN CNN LSTMSpeaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).
Stars: ✭ 56 (+229.41%)
Mutual labels: recurrent-neural-networks
AttentionGatedVNet3DAttention Gated VNet3D Model for KiTS19——2019 Kidney Tumor Segmentation Challenge
Stars: ✭ 35 (+105.88%)
Mutual labels: segmentation