Pinned Repositories
autoencoders_mnist
Different types of autoencoders illustrated on MNIST using TensorFlow.
bayes_gmm
Bayesian Gaussian mixture models in Python.
couscous
Siamese neural networks for representation learning using Theano.
data414
Data Analytics 414
eskmeans
Embedded segmental K-means (ES-KMeans) in Python.
lecture_dtw_notebook
nlp817
Natural Language Processing 817
recipe_swbd_wordembeds
speech_dtw
Dynamic time warping (DTW) functions for specifically speech alignment.
vqwordseg
Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.
kamperh's Repositories
kamperh/lecture_dtw_notebook
kamperh/bayes_gmm
Bayesian Gaussian mixture models in Python.
kamperh/data414
Data Analytics 414
kamperh/vqwordseg
Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.
kamperh/speech_dtw
Dynamic time warping (DTW) functions for specifically speech alignment.
kamperh/nlp817
Natural Language Processing 817
kamperh/eskmeans
Embedded segmental K-means (ES-KMeans) in Python.
kamperh/globalphone_awe
Multilingual acoustic word embedding approaches applied and evaluated on GlobalPhone data.
kamperh/suzerospeech2019
Stellenbosch University ZeroSpeech 2019 System
kamperh/recipe_bucktsong_awe_py3
Unsupervised acoustic word embeddings evaluated on Buckeye English and NCHLT Xitsonga data in Python 3.
kamperh/recipe_vision_speech_flickr
Using computer vision to ground unlabelled speech.
kamperh/recipe_bucktsong_awe
Unsupervised acoustic word embeddings evaluated on Buckeye English and NCHLT Xitsonga data in Python 2.7.
kamperh/stellenbosch_ee_report_template
A LaTeX template for reports following the guidelines of the E&E department at Stellenbosch University.
kamperh/yfacc
YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
kamperh/kamperh.github.io
kamperh/recipe_semantic_flickraudio
Semantic speech retrieval with a visually grounded model of untranscribed speech.
kamperh/bucktsong_eskmeans
Unsupervised segmentation and clustering of the Buckeye English and NCHLT Xitsonga datasets using the ES-KMeans algorithm.
kamperh/dpdp_aernn
Duration-penalized dynamic programming (DPDP) autoencoding recurrent neural network (AE-RNN) in Python.
kamperh/flickr_semantic_qbe_eval
Evaluation code for semantic QbE on the Flickr8k Audio Captions Corpus
kamperh/teaching_portfolio
Teaching Portfolio
kamperh/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
kamperh/babaloon
Speech processing in early childhood education
kamperh/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.
kamperh/masakhane
Let's put Africa on the Machine Translation Map!
kamperh/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.
kamperh/special-octo-palm-tree
kamperh/VectorQuantizedCPC
Vector-Quantized Contrastive Predictive Coding for Acoustic Unit Discovery and Voice Conversion
kamperh/weaklysupervised
kamperh/ZeroSpeech
VQ-VAE for Acoustic Unit Discovery and Voice Conversion
kamperh/zerospeech2021_baseline
BERT and LSTM baseline models of the ZeroSpeech Challenge 2021