*INFO needed on vowel extraction of speech***

Article View: comp.dsp

Article #98

#98

From: aux
Date: Sun, 09 Aug 1992 17:59

13 lines
1016 bytes

Hi, I require to identify the voiced segments of a speech records.  IT is my
understanding that, initially the data has to be initially broken down into
segments and then a decision as to voiced or non-voiced has to be made. One
could then go on and extract the pitch too. 

I have a paper by John Markel called the SIFT algorithm for fundamental
frequency estimation (1972) which seems the right paper.
I was wondering if you know of more recent  papers, books or any other source of
information which address this question. Source code would also be appreciated.

Thank you in advance for your time.

Hessam Bahari

Technical Details

Message-ID: <aux.713383147@Leland>

Path: arc1-ca.pugleaf.net!sparky!uunet!stanford.edu!leland.Stanford.EDU!Leland!aux

Show Full Headers

Complete Article Headers

Newsgroups: comp.dsp
Path: arc1-ca.pugleaf.net!sparky!uunet!stanford.edu!leland.Stanford.EDU!Leland!aux
From: aux@leo.Stanford.EDU (aux)
Subject: *INFO needed on vowel extraction of speech***
Message-ID: <aux.713383147@Leland>
Keywords: voiced, vonvoiced, pitch extraction
Sender: news@leland.Stanford.EDU (Mr News)
Organization: DSO, Stanford University
Date:  9 Aug 92 17:59:07 GMT
Lines: 13