1
MATLABAudioDatabaseToolbox
UserManual
Version1.00,July2008
MatlabADT was developed at the Signal and Image Processing Lab (SIPL)
,
DepartmentofElectricalEngineering
,Technion‐IIT,allrightsresevered.
(c)2008,Technion–IIT.
2
Table of Contents
Introduction ................................................................................................................... 3
QuickStart ..................................................................................................................... 4
FunctionOverview .......................................................................................................... 6
FunctionReferenceGuide ............................................................................................... 7
UsageExamples ............................................................................................................ 10
Appendix‐TIMIT/NTIMITFields ..................................................................................... 11
3
Introduction
MatlabADT (Audio Database Toolbox) enables easy access and filtering of audio
databasessuchasTIMITandYOHObytheirmetadata.Thedatabasetoolboxcomes
toreplacethemanualfilteringandcustomcodingusuallyrequiredforaccessingsuch
databases.Thistoolboxwillsaveyouthelearningtimeofthedatabasestructureand
willenableyoutofocusonalgorithmicaspectsofyourcode.
Thefollowingdatabasesaresupported:
1. TIMIT‐AcousticPhoneticContinuousSpeechCorpus(American‐English).
Supportedsearchcriteria:word,phoneme,usage,sex,dialect,speakerand
sentence.FormoreinformationonTIMITseetheappendixattheendofthis
document.
2. NTIMIT‐TelephoneNetworkAcousticPhoneticContinuousSpeechCorpus.
Supportedsearchcriteria:word,phoneme,usage,sex,dialect,speakerand
sentence.FormoreinformationonNTIMITseetheappendixattheendofthis
document.
3. CTIMIT‐CellularTelephoneAcousticPhoneticContinuousSpeechCorpus.
4. YOHO‐SpeakerVerificationCorpus.Supportedsearchcriteria:usage,speaker,
session,numbers.
5. TI‐Digits‐Speaker‐Independentrecognitionofconnecteddigitsequences.
Supportedsearchcriteria:usage,group,type,speakeranddigit.
6. ChildrenVoices‐HebrewSpeech.
7. HebrewBGU‐Hebrewwordsampleswere.
8. GutenbergBooks‐MP3formatbooks.
For more information on database structures
see the database documentation
availableontheSIPLsite.
ForanyprobleminusingMatlabADTpleasecontact:matlab_adt@sipl.technion.ac.il
4
Quick Start
InstallationoutsideofSIPL:
a. Extractthefilesandadd"MatlabADT"directorytoyourMATLABpath.
b. InMATLAB,executethecommand:
db=ADT('timit','C:\timit_path_on_your_computer','setup');
ThiswillloadTIMITandsetthedefaultpathtothedirectoryentered.
ForNTIMITorCTIMITruncorrespondingcommands.
c. Incaseyouwanttouseotherdatabases:inMatlabADT\@gendb\instance
directoryenterthesubdirectoriesandchangedefalt_path.txttothe
directoryofthespecificdatabaseonyourcomputer.
InstallationatSIPLworkstations:
a. Add the "sipl_matlab_utils" directory to the MATLAB path by executing the
command:addpath('\\piano\Data\sipl_matlab_utils'); or by using MATLAB
menus.
b. Executethecommandtimitdemo();tocheckinstallation.
Usage:
1. Loadthedesireddatabase
Loadingthedatabaseobject:
Databasename Loadingcommand
TIMIT db=ADT('timit');
NTIMIT db=ADT('ntimit');
CTIMIT db=ADT('ctimit');
YOHO db=gendb('yoho');
Ti‐Digits db=gendb('tidigits');
ChildrenVoices db=gendb('childrenvoices');
HebrewBGU db=gendb('hebrewbgu');
GutenbergBooks db=gendb('gutenbergbooks');
ll operations on the database will be performed using the database object whichis
passedtothemasthefirstparameter.
2. Make aqueryforyourwanteddata
[wavdata]=query(db,'dialect','dr1','word',{'she','it'},30);
Thiscalltothequeryfunctionwillreturnthewavedataofthefirst30words'she'
or'it'formdialect'dr1'intheformofacellarray