@inproceedings{laskowski-edlund-2010-snack,
title = "A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm",
author = "Laskowski, Kornel and
Edlund, Jens",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/576_Paper.pdf",
abstract = "Intonation is an important aspect of vocal production, used for a variety of communicative needs. Its modeling is therefore crucial in many speech understanding systems, particularly those requiring inference of speaker intent in real-time. However, the estimation of pitch, traditionally the first step in intonation modeling, is computationally inconvenient in such scenarios. This is because it is often, and most optimally, achieved only after speech segmentation and recognition. A consequence is that earlier speech processing components, in todays state-of-the-art systems, lack intonation awareness by fiat; it is not known to what extent this circumscribes their performance. In the current work, we present a freely available implementation of an alternative to pitch estimation, namely the computation of the fundamental frequency variation (FFV) spectrum, which can be easily employed at any level within a speech processing system. It is our hope that the implementation we describe aid in the understanding of this novel acoustic feature space, and that it facilitate its inclusion, as desired, in the front-end routines of speech recognition, dialog act recognition, and speaker recognition systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laskowski-edlund-2010-snack">
<titleInfo>
<title>A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kornel</namePart>
<namePart type="family">Laskowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Edlund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Intonation is an important aspect of vocal production, used for a variety of communicative needs. Its modeling is therefore crucial in many speech understanding systems, particularly those requiring inference of speaker intent in real-time. However, the estimation of pitch, traditionally the first step in intonation modeling, is computationally inconvenient in such scenarios. This is because it is often, and most optimally, achieved only after speech segmentation and recognition. A consequence is that earlier speech processing components, in todays state-of-the-art systems, lack intonation awareness by fiat; it is not known to what extent this circumscribes their performance. In the current work, we present a freely available implementation of an alternative to pitch estimation, namely the computation of the fundamental frequency variation (FFV) spectrum, which can be easily employed at any level within a speech processing system. It is our hope that the implementation we describe aid in the understanding of this novel acoustic feature space, and that it facilitate its inclusion, as desired, in the front-end routines of speech recognition, dialog act recognition, and speaker recognition systems.</abstract>
<identifier type="citekey">laskowski-edlund-2010-snack</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/576_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm
%A Laskowski, Kornel
%A Edlund, Jens
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F laskowski-edlund-2010-snack
%X Intonation is an important aspect of vocal production, used for a variety of communicative needs. Its modeling is therefore crucial in many speech understanding systems, particularly those requiring inference of speaker intent in real-time. However, the estimation of pitch, traditionally the first step in intonation modeling, is computationally inconvenient in such scenarios. This is because it is often, and most optimally, achieved only after speech segmentation and recognition. A consequence is that earlier speech processing components, in todays state-of-the-art systems, lack intonation awareness by fiat; it is not known to what extent this circumscribes their performance. In the current work, we present a freely available implementation of an alternative to pitch estimation, namely the computation of the fundamental frequency variation (FFV) spectrum, which can be easily employed at any level within a speech processing system. It is our hope that the implementation we describe aid in the understanding of this novel acoustic feature space, and that it facilitate its inclusion, as desired, in the front-end routines of speech recognition, dialog act recognition, and speaker recognition systems.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/576_Paper.pdf
Markdown (Informal)
[A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm](http://www.lrec-conf.org/proceedings/lrec2010/pdf/576_Paper.pdf) (Laskowski & Edlund, LREC 2010)
ACL