Subject: Re: Help with alignment tool for speech database From: Mark Huckvale <m.huckvale@xxxxxxxx> Date: Sat, 30 Jun 2007 10:13:15 +0100 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>Dear Xinhui There is a tool ("analign") for aligning British English phonetic transcription with audio within the SFS toolkit: http://www.phon.ucl.ac.uk/resource/sfs/ But it is a little tricky to set up. The HowTo at http://www.phon.ucl.ac.uk/resource/sfs/howto/transcribe.htm may help. Inside it just uses code borrowed from the Hidden Markov Model Toolkit HTK (http://htk.eng.cam.ac.uk/). So you might instead choose this to build a version specific to your requirements. Regards Mark Huckvale xinhui zhou wrote: > Hi, All, > > I am interested in some automatic or semiautomatic alignment tool for > a speech database, X-ray Microbeam Production database (XRMB-SPD). > > We have the speech signal and also the transcripts, and would like to > put phonetic labels aligned with the speech signal. It will be good > if we can use automatic tool first and then correct the alignment > manually. > > Thanks in advance, > > Xinhui Zhou -- Mark Huckvale, Director MSc Speech and Hearing Science Phonetics and Linguistics, University College London www.phon.ucl.ac.uk