Learning similarity functions for pronunciation variations

Einat Naaman, Yossi Adi, Joseph Keshet

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations


A significant source of errors in Automatic Speech Recognition (ASR) systems is due to pronunciation variations which occur in spontaneous and conversational speech. Usually ASR systems use a finite lexicon that provides one or more pronunciations for each word. In this paper, we focus on learning a similarity function between two pronunciations. The pronunciations can be the canonical and the surface pronunciations of the same word or they can be two surface pronunciations of different words. This task generalizes problems such as lexical access (the problem of learning the mapping between words and their possible pronunciations), and defining word neighborhoods. It can also be used to dynamically increase the size of the pronunciation lexicon, or in predicting ASR errors. We propose two methods, which are based on recurrent neural networks, to learn the similarity function. The first is based on binary classification, and the second is based on learning the ranking of the pronunciations. We demonstrate the efficiency of our approach on the task of lexical access using a subset of the Switchboard conversational speech corpus. Results suggest that on this task our methods are superior to previous methods which are based on graphical Bayesian methods.

Original languageEnglish
Pages (from-to)2561-2565
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 2017
Event18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017

Bibliographical note

Publisher Copyright:
Copyright © 2017 ISCA.


Dive into the research topics of 'Learning similarity functions for pronunciation variations'. Together they form a unique fingerprint.

Cite this