- bayes_gmm: Bayesian Gaussian mixture models in Python, as described in SLT’14.
- speech_correspondence: Pylearn2 implementation of the correspondence autoencoder, as described in ICASSP’15.
- couscous: Theano code for training Siamese CNNs. We used it in ICASSP’16 for training acoustic word embeddings from speech, as shown in this complete recipe.
- segmentalist: Unsupervised word segmentation and clustering of speech in Python. A complete recipe is coming soon.
Hopefully someone else might also find these notes useful. Let me know if you find any mistakes or have any comments.
- Gibbs sampling for fitting finite and infinite Gaussian mixture models. [pdf, code]
- Vector and matrix calculus. [pdf]
- MIT, Computer Science and Artificial Intelligence Laboratory, 2016.
Unsupervised neural and Bayesian models for zero-resource speech processing. [slides]
- Workshop on Machine Learning in Speech and Language Processing, Spotlight Speaker, 2016.
Unsupervised speech processing using acoustic word embeddings. [slides]