From LinguisticAnnotation
Jump to: navigation, search
 
 
Line 1: Line 1:
[http://cslu.cse.ogi.edu/toolkit CSLU]  ([mailto:shobaki@cse.ogi.edu,jacques@cse.ogi.edu  Kal Shobaki, Jacques De Villiers]) <br /> The CSLU Speech Toolkit, developed at the Center for Spoken Language Understanding (CSLU) has a complete set of free tools for collecting and transcribing speech. It contains an interactive speech display program (Speech View) which allows the user to align transcripts with the sound files. The toolkit also contains a complete [http://cslu.cse.ogi.edu/tutordemos course] in spectrogram reading and acoustic phonetics, a speech recognition engine, a speech synthesizer based on the [#Festival Festival architecture], a facial animation component, and an integration tool for authoring your own spoken language system. CSLU also has an ascii encoding for phonetic transcriptions ([ftp://speech.cse.ogi.edu/pub/docs/worldbet.ps  large postscript file]).
+
[http://cslu.cse.ogi.edu/toolkit CSLU]  ([mailto:shobaki@cse.ogi.edu,jacques@cse.ogi.edu  Kal Shobaki, Jacques De Villiers]) <br /> The CSLU Speech Toolkit, developed at the Center for Spoken Language Understanding (CSLU) has a complete set of free tools for collecting and transcribing speech. It contains an interactive speech display program (Speech View) which allows the user to align transcripts with the sound files. The toolkit also contains a complete [http://cslu.cse.ogi.edu/tutordemos course] in spectrogram reading and acoustic phonetics, a speech recognition engine, a speech synthesizer based on the [#Festival Festival architecture], a facial animation component, and an integration tool for authoring your own spoken language system. CSLU also has an ascii encoding for phonetic transcriptions.

Latest revision as of 16:55, 4 October 2006

CSLU (Kal Shobaki, Jacques De Villiers)
The CSLU Speech Toolkit, developed at the Center for Spoken Language Understanding (CSLU) has a complete set of free tools for collecting and transcribing speech. It contains an interactive speech display program (Speech View) which allows the user to align transcripts with the sound files. The toolkit also contains a complete course in spectrogram reading and acoustic phonetics, a speech recognition engine, a speech synthesizer based on the [#Festival Festival architecture], a facial animation component, and an integration tool for authoring your own spoken language system. CSLU also has an ascii encoding for phonetic transcriptions.