Research Area:  Machine Learning
Fixed-length embeddings of words are very useful for a variety of tasks in speech and language processing. Here we systematically explore two methods of computing fixed-length embeddings for variable-length sequences. We evaluate their susceptibility to phonetic and speaker-specific variability on English, a high resource language and Xitsonga, a low resource language, using two evaluation metrics: ABX word discrimination and ROC-AUC on same-different phoneme n-grams. We show that a simple downsampling method supplemented with length information can outperform the variable-length input feature representation on both evaluations. Recurrent autoencoders, trained without supervision, can yield even better results at the expense of increased computational complexity.
Keywords:  
Learning Word Embeddings
Unsupervised
Machine Learning
Deep Learning
Author(s) Name:  Nils Holzenberger , Mingxing Du ,Julien Karadayi,Rachid Riad,Emmanuel Dupoux
Journal name:  
Conferrence name:  Cognitive science
Publisher name:  HAL
DOI:  10.21437/Interspeech.2018-2364
Volume Information:  
Paper Link:   https://hal.archives-ouvertes.fr/hal-01888708/