From mfleck at cs.uiuc.edu  Fri Jan 26 14:51:56 2007
From: mfleck at cs.uiuc.edu (Margaret Fleck)
Date: Fri, 26 Jan 2007 14:51:56 -0600
Subject: [nl-uiuc] [Fwd: Linguistics Seminar (next week/G17)]
Message-ID: <45BA69EC.4040306@cs.uiuc.edu>



-------- Original Message --------
Subject: Linguistics Seminar (next week/G17)
Date: Fri, 26 Jan 2007 10:23:59 -0600
From: Eunah Kim <ekim39 at uiuc.edu>
Reply-To: ekim39 at uiuc.edu
To: LING-DEPT-L at LISTSERV.UIUC.EDU

Dear all,

Here is the information on the next seminar. Please note that the talk will be presented in G17, not 
in Lucy Ellis.
-------------------------------------------

Presenter: Tae-Jin Yoon (Ph.D. Candidate of the Linguistics Dept.)

Time: Thursday, February 1, 2007, 4PM,

Place: G17, FLB

Title:
Modeling Phonetics and Phonology for Speech Technology: Dual Advances in Linguistic Science and 
Engineering

Abstract:
In this talk, I present two distinct, but related research goals: One is improving automatic speech 
recognition using phonetic knowledge, and the other is finding phonetic encoding of linguistic 
structure with the aid of automatic speech recognition.

In the first part of the talk, I demonstrate that phonetic knowledge can be used in improving the 
performance of automatic speech recognition. Specifically, I show that spectral and temporal 
measurements of speech sounds that are related to voice quality can be used in improving word 
recognition accuracy in automatic speech recognition system. The spectral measurement of H1-H2 and 
the temporal measurement of the mean autocorrelation ratio are used to objectively label voice 
quality categories on each sonorant phone on a subset of Switchboard corpus (Godfrey et al. 1992). 
Results from a Support Vector Machine (SVM) classification experiment show that these features are 
predictive of Perceptual Linear Predictive Cepstra (PLPC, Hermansky 1990) that are used as an input 
to speech recognition. I further demonstrate that by incorporating voice quality knowledge into a 
speech recognition system, we can improve word recognition accuracy. Acoustic phonetic models of 
voice quality, th!
  us!
, lead to improved speech technology.

In the second part of the talk, I illustrate that tools from speech technology, in turn, can be used 
for linguistic analysis, enabling the analysis of large-scale databases, and incorporating 
laboratory and non-laboratory recordings. In particular, the phonetic encoding of prosodic structure 
is investigated through a study of the acoustic correlates of prosodic boundary and their 
interaction with accent at three levels of prosodic phrasing, with the three phrasing levels being 
word, intermediate phrase, and intonational phrase (see Ladd 1996). Acoustic cues to prosodic 
boundaries are observed in the lengthening of segments in the preboundary syllable rhyme, with 
greater effects of lengthening at successively higher levels of prosodic domains (Wightman et al. 
1992). A second dimension of prosodic structure is the encoding of prominence, which also gives rise 
to lengthening effects in the prominent syllable (stressed or accented) (Turk and Sawusch 1997). 
Given two distinct sou!
  rc!
es of lengthening, the question arises whether lengthening on its own can serve as a cue to either 
prosodic context. For the analysis, we obtained a large amount of phone-aligned data from Boston 
University Radio News Corpus (Ostendorf et al. 1995) using forced alignment based on HMM (Hidden 
Markov Model). I present results showing effects of prosodic boundary and accent at the three 
prosodic levels in measures of duration local to the domain-final rhyme.

In conclusion, phonetics and phonology provide an important source of knowledge for the design of 
speech technologies, and speech technologies provide useful and crucial aids for the investigation 
of complex linguistic phenomena based on diverse and large-scale speech databases.

Eunah

From mfleck at cs.uiuc.edu  Tue Jan 30 13:10:30 2007
From: mfleck at cs.uiuc.edu (Margaret M. Fleck)
Date: Tue, 30 Jan 2007 13:10:30 -0600
Subject: [nl-uiuc] [Fwd: [cogcomp] Eugene Charniak here next Monday]
Message-ID: <45BF9826.109@cs.uiuc.edu>


Looks like Eugene Charniak is talking in the CS Dept, Monday 5 Feb, 
4-5pm.     See calendar entry:

http://webtools.uiuc.edu/calendar/Calendar?ACTION=VIEW_EVENT&calId=504&skinId=47&DATE=1/28/2007&eventId=37541 
<http://webtools.uiuc.edu/calendar/Calendar?ACTION=VIEW_EVENT&calId=504&skinId=47&DATE=1/28/2007&eventId=37541>

Nope, I don't have an abstract or anything.   We're real disorganized 
over here in CS.

Cheers,

Margaret


-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: file:///tmp/nsmail.asc
Url: http://lists.cs.uiuc.edu/pipermail/nl-uiuc/attachments/20070130/30622976/attachment.asc 

From rws at uiuc.edu  Tue Jan 30 14:38:21 2007
From: rws at uiuc.edu (Richard Sproat)
Date: Tue, 30 Jan 2007 14:38:21 -0600 (CST)
Subject: [nl-uiuc] [Fwd: [cogcomp] Eugene Charniak here next Monday]
Message-ID: <20070130143821.AIT50612@expms6.cites.uiuc.edu>

Thanks!

Once again, if it had not been for you I would not have heard about this.

Does CS ever advertise things (except via good citizens like you)? 

---- Original message ----
>Date: Tue, 30 Jan 2007 13:10:30 -0600
>From: "Margaret M. Fleck" <mfleck at cs.uiuc.edu>  
>Subject: [nl-uiuc] [Fwd: [cogcomp] Eugene Charniak here next Monday]  
>To: nl-uiuc at cs.uiuc.edu
>
>
>Looks like Eugene Charniak is talking in the CS Dept, Monday 5 Feb, 
>4-5pm.     See calendar entry:
>
>http://webtools.uiuc.edu/calendar/Calendar?ACTION=VIEW_EVENT&calId=504&skinId=47&DATE=1/28/2007&eventId=37541 
><http://webtools.uiuc.edu/calendar/Calendar?ACTION=VIEW_EVENT&calId=504&skinId=47&DATE=1/28/2007&eventId=37541>
>
>Nope, I don't have an abstract or anything.   We're real disorganized 
>over here in CS.
>
>Cheers,
>
>Margaret
>
>
>________________
>_______________________________________________
>cogcomp mailing list
>cogcomp at cs.uiuc.edu
>http://lists.cs.uiuc.edu/mailman/listinfo/cogcomp
>
>________________
>_______________________________________________
>nl-uiuc mailing list
>nl-uiuc at cs.uiuc.edu
>http://lists.cs.uiuc.edu/mailman/listinfo/nl-uiuc

From mfleck at cs.uiuc.edu  Wed Jan 31 11:13:08 2007
From: mfleck at cs.uiuc.edu (Margaret M. Fleck)
Date: Wed, 31 Jan 2007 11:13:08 -0600
Subject: [nl-uiuc] [Fwd: DISTINGUISHED LECTURESHIP SERIES, Eugene Charniak,
	Feb. 5]
Message-ID: <45C0CE24.3000500@cs.uiuc.edu>



-------- Original Message --------
Subject: 	DISTINGUISHED LECTURESHIP SERIES, Eugene Charniak, Feb. 5
Date: 	Wed, 31 Jan 2007 10:56:07 -0600
From: 	Erna A Amerman <erna at cs.uiuc.edu>
To: 	<ifaculty at cs.uiuc.edu>
CC: 	<clerical at cs.uiuc.edu>



Prof. Gerald DeJong is the host assisted by Ronda Pellegrini at 
rpellegr at cs.uiuc.edu.

 

 

 

University of Illinois at Urbana-Champaign

Department of Computer Science

The Thomas M. Siebel Center for Computer Science

201 North Goodwin Avenue

Urbana, Illinois 61801-2302  USA

 

 

*/ /*

*/DISTINGUISHED LECTURESHIP SERIES/*

*/ (and Graduate Seminar)/*

 

 

 


        */Recent Results in Parsing/*


  */ /**//*

                                               

Eugene Charniak

                                                Department of Computer 
Science


            Brown University

 

February 5 (Monday), 2007 at 4:00 p.m.

                                                1404 Siebel Center for 
Computer Science

 

                                               

Parsing is the problem of mapping a string (in, say, English) to a 
phrase structure.  It is important because it gives us a first rough cut 
at meaning.  During the 1990s there was a flurry of new results using 
statistical techniques that gave us our first robust parsers ready for 
every-day use.  While there has been continued results since then, the 
practical parsers at the start of 2005 were no better than what has 
available in 2000.  The first part of the talk will recap this ancient 
history.

 

The last two years, however, have seen a dramatic turn-around with error 
rates decreasing by 25%.  The second and third parts of the talk 
describe the two techniques responsible for this state of affairs: 
discriminative reranking and self training.  We also show that the 
latest results seem to be less corpus specific than the previous 
results.  (That is, they carry over to text corpora reasonably different 
than those upon which they were trained.

 

 

Bio:

Eugene Charniak is University Professor of Computer Science and 
Cognitive Science at Brown University and past chair of the Department 
of Computer Science.  He received his A.B. degree in Physics from 
University of Chicago, and a Ph.D. from M.I.T. in Computer Science.  He 
has published four books the most recent being Statistical Language 
Learning.  He is a Fellow of the American Association of Artificial 
Intelligence and was previously a Councilor of the organization.  His 
research has always been in the area of language understanding or 
technologies which relate to it.  Over the last 15 years he has been 
interested in statistical techniques for parsing, speech recognition, 
and other areas of language processing.

 

 

Reception after the talk in the 2^nd Floor Atrium of Siebel Center.

 

 

If you would like to subscribe to announcement:  

http://mail.cs.uiuc.edu/mailman/listinfo/announce

 

-------------- next part --------------
A non-text attachment was scrubbed...
Name: POSTER Feb. 5, DLS Eugene Charniak (DeJong-RP).doc
Type: application/msword
Size: 32256 bytes
Desc: not available
Url : http://lists.cs.uiuc.edu/pipermail/nl-uiuc/attachments/20070131/3d9485c6/attachment-0001.doc