Publications by Alex Gutkin
s9900835.bib
@inproceedings{Gutkin:Gay:qr05,
author = {Alexander Gutkin and David R. Gay},
title = {{S}tructural {R}epresentation and {M}atching of
{A}rticulatory {S}peech {S}tructures based on the
{E}volving {T}ransformation {S}ystem ({ETS})
{F}ormalism},
booktitle = {Proc. 19th International Workshop on Qualitative
Reasoning (QR-05)},
editor = {Michael Hofbaur and Bernhard Rinner and Franz Wotawa},
pages = {89--96},
address = {Graz, Austria},
abstract = { A formal structural representation of speech
consistent with the principles of combinatorial
structure theory is presented in this paper. The
representation is developed within the Evolving
Transformation System (ETS) formalism and encapsulates
speech processes at the articulatory level. We show how
the class structure of several consonantal phonemes of
English can be expressed with the help of articulatory
gestures---the atomic combinatorial units of speech. As
a preliminary step towards the design of a speech
recognition architecture based on the structural
approaches to physiology and articulatory phonology, we
present an algorithm for the structural detection of
phonemic class elements inside gestural ETS structures
derived from continuous speech. Experiments designed to
verify the adequacy of the hypothesised gestural class
structure conducted on the MOCHA articulatory corpus
are then described. Our experimental results support
the hypothesis that the articulatory representation
captures sufficient information for the accurate
structural identification of the phonemic classes in
question. },
categories = {structural,recognition,ets,artic,mocha,edinburgh,unb},
isbn = {3-9502019-0-4},
month = may,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_gay_qr05.pdf},
year = 2005
}
@mastersthesis{Gutkin:00,
author = {Alexander Gutkin},
title = {{L}og-{L}inear {I}nterpolation of {L}anguage {M}odels},
school = {Department of Engineering, University of Cambridge},
type = {{MPhil.} thesis},
address = {UK},
categories = {statistical speech recognition, language modelling},
month = dec,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2000/gutkin_mphil.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2000/gutkin_mphil.ps.gz},
year = 2000
}
@inproceedings{Gutkin:King:pris05,
author = {Alexander Gutkin and Simon King},
title = {{I}nductive {S}tring {T}emplate-{B}ased {L}earning of
{S}poken {L}anguage},
booktitle = {Proc. 5th International Workshop on Pattern
Recognition in Information Systems (PRIS-2005), In
conjunction with the 7th International Conference on
Enterprise Information Systems (ICEIS-2005)},
editor = {Hugo Gamboa and Ana Fred},
pages = {43--51},
address = {Miami, USA},
publisher = {INSTICC Press},
abstract = { This paper deals with formulation of alternative
structural approach to the speech recognition problem.
In this approach, we require both the representation
and the learning algorithms defined on it to be
linguistically meaningful, which allows the speech
recognition system to discover the nature of the
linguistic classes of speech patterns corresponding to
the speech waveforms. We briefly discuss the current
formalisms and propose an alternative --- a
phonologically inspired string-based inductive speech
representation, defined within an analytical framework
specifically designed to address the issues of class
and object representation. We also present the results
of the phoneme classification experiments conducted on
the TIMIT corpus of continuous speech. },
categories = {structural,recognition,acoustic,phonetic_feature,timit,edinburgh},
isbn = {972-8865-28-7},
month = may,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_king_pris05.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_king_pris05.ps.gz},
year = 2005
}
@inproceedings{Gutkin:King:icslp04,
author = {Alexander Gutkin and Simon King},
title = {Phone classification in pseudo-{E}uclidean Vector
Spaces},
booktitle = {Proc. 8th International Conference on Spoken Language
Processing (ICSLP)},
volume = {II},
pages = {1453--1457},
address = {Jeju Island, Korea},
abstract = { Recently we have proposed a structural framework for
modelling speech, which is based on patterns of
phonological distinctive features, a linguistically
well-motivated alternative to standard vector-space
acoustic models like HMMs. This framework gives
considerable representational freedom by working with
features that have explicit linguistic interpretation,
but at the expense of the ability to apply the wide
range of analytical decision algorithms available in
vector spaces, restricting oneself to more
computationally expensive and less-developed symbolic
metric tools. In this paper we show that a
dissimilarity-based distance-preserving transition from
the original structural representation to a
corresponding pseudo-Euclidean vector space is
possible. Promising results of phone classification
experiments conducted on the TIMIT database are
reported. },
categories = {structural,recognition,acoustic,phonetic_feature,timit,edinburgh},
issn = {1225-441x},
month = oct,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/gutkin_king_icslp04.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/gutkin_king_icslp04.ps.gz},
year = 2004
}
@inproceedings{Gutkin:King:icpr04,
author = {Alexander Gutkin and Simon King},
title = {{S}tructural {R}epresentation of {S}peech for
{P}honetic {C}lassification},
booktitle = {Proc. 17th International Conference on Pattern
Recognition (ICPR)},
volume = 3,
pages = {438--441},
address = {Cambridge, UK},
publisher = {IEEE Computer Society Press},
abstract = { This paper explores the issues involved in using
symbolic metric algorithms for automatic speech
recognition (ASR), via a structural representation of
speech. This representation is based on a set of
phonological distinctive features which is a
linguistically well-motivated alternative to the
``beads-on-a-string'' view of speech that is standard
in current ASR systems. We report the promising results
of phoneme classification experiments conducted on a
standard continuous speech task. },
categories = {structural,recognition,acoustic,phonetic_feature,timit,edinburgh},
isbn = {0-7695-2128-2},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/gutkin_king_icpr04.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/gutkin_king_icpr04.ps.gz},
year = 2004
}
@inproceedings{Gutkin:King:icassp05,
author = {Alexander Gutkin and Simon King},
title = {{D}etection of {S}ymbolic {G}estural {E}vents in
{A}rticulatory {D}ata for {U}se in {S}tructural
{R}epresentations of {C}ontinuous {S}peech},
booktitle = {Proc. IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP-05)},
volume = {I},
pages = {885--888},
address = {Philadelphia, PA, USA},
publisher = {IEEE Signal Processing Society Press},
abstract = { One of the crucial issues which often needs to be
addressed in structural approaches to speech
representation is the choice of fundamental symbolic
units of representation. In this paper, a
physiologically inspired methodology for defining these
symbolic atomic units in terms of primitive
articulatory events is proposed. It is shown how the
atomic articulatory events (gestures) can be detected
directly in the articulatory data. An algorithm for
evaluating the reliability of the articulatory events
is described and promising results of the experiments
conducted on MOCHA articulatory database are presented.
},
categories = {structural,recognition,artic,mocha,edinburgh},
isbn = {0-7803-8875-5},
month = mar,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_king_icassp2005.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_king_icassp2005.ps.gz},
year = 2005
}
@inproceedings{Gutkin:etal:ets-cam04,
author = {Alexander Gutkin and David Gay and Lev Goldfarb and
Mirjam Wester},
title = {On the {A}rticulatory {R}epresentation of {S}peech
within the {E}volving {T}ransformation {S}ystem
{F}ormalism},
booktitle = {Pattern Representation and the Future of Pattern
Recognition (Proc. Satellite Workshop of 17th
International Conference on Pattern Recognition)},
editor = {Lev Goldfarb},
pages = {57--76},
address = {Cambridge, UK},
abstract = { This paper deals with the formulation of an
alternative, structural, approach to the speech
representation and recognition problem. In this
approach, we require both the representation and the
learning algorithms to be linguistically meaningful and
to naturally represent the linguistic data at hand.
This allows the speech recognition system to discover
the emergent combinatorial structure of the linguistic
classes. The proposed approach is developed within the
ETS formalism, the first formalism in applied
mathematics specifically designed to address the issues
of class and object/event representation. We present an
initial application of ETS to the articulatory
modelling of speech based on elementary physiological
gestures that can be reliably represented as the ETS
primitives. We discuss the advantages of this gestural
approach over prevalent methods and its promising
potential to mathematical modelling and representation
in linguistics. },
categories = {structural,recognition,ets,artic,mocha,edinburgh,unb},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/ets_cam04_dasr.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/ets_cam04_dasr.ps.gz},
year = 2004
}
@phdthesis{Gutkin:phd:05,
author = {Alexander Gutkin},
title = {{T}owards {F}ormal {S}tructural {R}epresentation of
{S}poken {L}anguage: {A}n {E}volving {T}ransformation
{S}ystem ({ETS}) {A}pproach},
school = {School of Informatics, University of Edinburgh},
address = {UK},
note = {Internal version},
categories = {structural,representation,recognition,edinburgh,unb,ets},
month = dec,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_phd_full.pdf},
year = 2005
}
@inproceedings{Gutkin:Gay:ijcai05,
author = {Alexander Gutkin and David R. Gay},
title = {Structural Representation and Matching of Articulatory
Speech Structures based on the Evolving Transformation
System ({ETS}) Formalism},
booktitle = {Proc. Nineteenth International Joint Conference on
Artificial Intelligence (IJCAI-05)},
address = {Edinburgh, UK},
categories = {structural,recognition,ets,artic,mocha,edinburgh,unb},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/gutkin_gay_ijcai05.pdf},
year = 2005
}
![[ intranet ]](/images/menu_intranet.png)
![[ festival ]](/images/menu_festival.png)