[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: objective segmenting
- To: AUDITORY@xxxxxxxxxxxxxxx
- Subject: Re: objective segmenting
- From: Stefan Crawcour <stephen_crawcour@xxxxxxxxx>
- Date: Sat, 19 Nov 2005 04:35:36 -0800
- Delivery-date: Sat Nov 19 07:49:13 2005
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=nR5upTTgLsGo33vS83r+TLRCKDH3XPwL4Q/dT58uxIBfaR14tCbFSwLHlCOd5vfWLdPNNe3inWjCIshyMhW2ssJe/dh3baa4Kah8CMmmz8pGRn5GIEJt7xVzU0gm9bx7ciEeeg7r0w0kGrKbn2w2kF2a0XdcDRkj4poLLLi3b9c= ;
- In-reply-to: <AUDITORY%200511190000157720.3F27@LISTS.MCGILL.CA>
- Reply-to: Stefan Crawcour <stephen_crawcour@xxxxxxxxx>
- Sender: AUDITORY Research in Auditory Perception <AUDITORY@xxxxxxxxxxxxxxx>
thank you very much for your reply and the bibliographic references. I fully agree with your statement, when applied to spontaneous speech. But what if we are dealing with the same sentence that is read by different people ? Here the distinction between nouns and verbs should be clear. If for sentences read aloud, I decided to take the following criterion: segment sound [a] from the word [kat] , and segment at the first formant value that carries a linear difference of more than so and so many Herz from the preceding formant value, would that serve my purpose, since the formant values are different for each sound ?
Yahoo! FareChase - Search multiple travel sites in one click.