kamperh Goto Github PK

allosaurus

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

autoencoders_mnist

Different types of autoencoders illustrated on MNIST using TensorFlow.

babaloon

Speech processing in early childhood education

bayes_gmm

Bayesian Gaussian mixture models in Python.

bucktsong_eskmeans

Unsupervised segmentation and clustering of the Buckeye English and NCHLT Xitsonga datasets using the ES-KMeans algorithm.

bucktsong_segmentalist

Unsupervised segmentation and clustering of Buckeye English and NCHLT Xitsonga corpora.

couscous

Siamese neural networks for representation learning using Theano.

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.

data414

Data Analytics 414

dpdp_aernn

Duration-penalized dynamic programming (DPDP) autoencoding recurrent neural network (AE-RNN) in Python.

eskmeans

Embedded segmental K-means (ES-KMeans) in Python.

flickr_semantic_qbe_eval

Evaluation code for semantic QbE on the Flickr8k Audio Captions Corpus

globalphone_awe

Multilingual acoustic word embedding approaches applied and evaluated on GlobalPhone data.

kamperh.github.io

lecture_dtw_notebook

masakhane

Let's put Africa on the Machine Translation Map!

ml-coursera-python-assignments

Python assignments for the machine learning class by andrew ng on coursera with complete submission for grading capability and re-written instructions.

nlp817

Natural Language Processing 817

recipe_bucktsong_awe

Unsupervised acoustic word embeddings evaluated on Buckeye English and NCHLT Xitsonga data in Python 2.7.

recipe_bucktsong_awe_py3

Unsupervised acoustic word embeddings evaluated on Buckeye English and NCHLT Xitsonga data in Python 3.

recipe_semantic_flickraudio

Semantic speech retrieval with a visually grounded model of untranscribed speech.

recipe_swbd_wordembeds

recipe_vision_speech_flickr

Using computer vision to ground unlabelled speech.

recipe_zs2017_track2

Recipe for applying the embedded segmental k-means model to the ZeroSpeech2017 Track 2 challenge.

segmentalist

Unsupervised word segmentation and clustering of speech

semantic_flickraudio

A data set of semantic keyword spotting labels for the Flickr Audio Captions Corpus.

special-octo-palm-tree

speech_correspondence

Correspondence and autoencoder neural network training for speech using Pylearn2.

speech_dtw

Dynamic time warping (DTW) functions for specifically speech alignment.

stellenbosch_ee_report_template

A LaTeX template for reports following the guidelines of the E&E department at Stellenbosch University.