A temporal coherence loss function for learning unsupervised acoustic embeddings
The Zero Resource Speech Challenge 2015: Proposed Approaches and Results
Joint Learning of Speaker and Phonetic Similarities with Siamese Networks
Discriminability of sound contrasts in the face of speaker variation quantified
The role of word-word co-occurrence in word learning
The 'Language Filter' Hypothesis: Modeling Language Separation in Infants using I-vectors
Quantificational features in distributional word representations
The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective
Learning words from images and speech
The Zero Resource Speech Challenge 2017