AUTOMATIC TOOLS FOR ANALYZING SPOKEN HEBREW

A Ben-Shalom, J Keshet, D Modan, A Laufer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work summarizes our project to propose a set of automatic tools for analyzing the phonetic and phonological content of spoken Hebrew. The goal of the project is to provide a set of resources to scientists and engineers who work on research and engineering problems related to the acoustics and linguistics of the modern Hebrew language. The set of tools includes: (i) a transcribed corpus of Modern Hebrew; (ii) a phonetic classifier; (iii) a forced aligner, and (iv) an automatic procedure for converting dotted (vowelized) orthographic transcription into phonemic transcription. This tool along with the forced aligner can be used to automatically align words and their phonemes to the speech signal. We are not familiar with any such publicly available corpus or tools for the Hebrew language.
Original languageAmerican English
Title of host publicationAfeka Conference for Speech Processing
StatePublished - 2014

Bibliographical note

Place of conference:Israel

Fingerprint

Dive into the research topics of 'AUTOMATIC TOOLS FOR ANALYZING SPOKEN HEBREW'. Together they form a unique fingerprint.

Cite this