Kosta Sokolov avatar Kosta Sokolov committed 377ab65

more to speech perception

Comments (0)

Files changed (4)

bib/etale_dimensionality_reduction.bib

 % This file was created with JabRef 2.7b.
 % Encoding: UTF-8
 
+@ARTICLE{belkin2004semi,
+  author = {Belkin, M. and Niyogi, P.},
+  title = {Semi-supervised learning on Riemannian manifolds},
+  journal = {Machine Learning},
+  year = {2004},
+  volume = {56},
+  pages = {209--239},
+  number = {1},
+  abstract = {We consider the general problem of utilizing both labeled and unlabeled
+	data to improve classification accuracy. Under the assumption that
+	the data lie on a submanifold in a high dimensional space, we develop
+	an algorithmic framework to classify a partially labeled data set
+	in a principled manner. The central idea of our approach is that
+	classification functions are naturally defined only on the submanifold
+	in question rather than the total ambient space. Using the Laplace-Beltrami
+	operator one produces a basis (the Laplacian Eigenmaps) for a Hilbert
+	space of square integrable functions on the submanifold. To recover
+	such a basis, only unlabeled examples are required. Once such a basis
+	is obtained, training can be performed using the labeled data set.
+	Our algorithm models the manifold using the adjacency graph for the
+	data and approximates the Laplace-Beltrami operator by the graph
+	Laplacian. We provide details of the algorithm, its theoretical justification,
+	and several practical applications for image, speech, and text classification.},
+  publisher = {Springer}
+}
+
 @ARTICLE{belkin2001laplacian,
   author = {Belkin, M. and Niyogi, P.},
   title = {Laplacian eigenmaps and spectral techniques for embedding and clustering},
   organization = {IEEE}
 }
 
+@INPROCEEDINGS{jain2004exploratory,
+  author = {Jain, V. and Saul, L.K.},
+  title = {Exploratory analysis and visualization of speech and music by locally
+	linear embedding},
+  booktitle = {Acoustics, Speech, and Signal Processing, 2004. Proceedings.(ICASSP'04).
+	IEEE International Conference on},
+  year = {2004},
+  volume = {3},
+  pages = {iii--984},
+  organization = {IEEE}
+}
+
+@BOOK{jolliffe2005principal,
+  title = {Principal component analysis},
+  publisher = {Wiley Online Library},
+  year = {2005},
+  author = {Jolliffe, I.}
+}
+
 @ARTICLE{ng2002spectral,
   author = {Ng, A.Y. and Jordan, M.I. and Weiss, Y. and others},
   title = {On spectral clustering: Analysis and an algorithm},
   publisher = {American Association for the Advancement of Science}
 }
 
+@ARTICLE{saul2003think,
+  author = {Saul, L.K. and Roweis, S.T.},
+  title = {Think globally, fit locally: unsupervised learning of low dimensional
+	manifolds},
+  journal = {The Journal of Machine Learning Research},
+  year = {2003},
+  volume = {4},
+  pages = {119--155},
+  publisher = {JMLR. org}
+}
+
 @ARTICLE{tenenbaum2000global,
   author = {Tenenbaum, J.B. and De Silva, V. and Langford, J.C.},
   title = {A global geometric framework for nonlinear dimensionality reduction},
   publisher = {American Association for the Advancement of Science}
 }
 
+@ARTICLE{van2009dimensionality,
+  author = {Van der Maaten, LJP and Postma, EO and Van Den Herik, HJ},
+  title = {Dimensionality reduction: A comparative review},
+  journal = {Journal of Machine Learning Research},
+  year = {2009},
+  volume = {10},
+  pages = {1--41},
+  abstract = {In recent years, a variety of nonlinear dimensionality reduction techniques
+	have been proposed that aim to address the limitations of traditional
+	techniques such as PCA. The paper presents a review and systematic
+	comparison of these techniques. The performances of the nonlinear
+	techniques are investigated on artificial and natural tasks. The
+	results of the experiments reveal that nonlinear techniques perform
+	well on selected artificial tasks, but do not outperform the traditional
+	PCA on real-world tasks. The paper explains these results by identifying
+	weaknesses of current nonlinear techniques, and suggests how the
+	performance of nonlinear dimensionality reduction techniques may
+	be improved.},
+  publisher = {Citeseer}
+}
+
 @INPROCEEDINGS{weinberger2004unsupervised,
   author = {Weinberger, K.Q. and Saul, L.K.},
   title = {Unsupervised learning of image manifolds by semidefinite programming},

bib/etale_manifold_learning_asr.bib

   citeulike-article-id = {3733361},
   citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.9400},
   keywords = {laplacian-eigenmaps, spectral},
-  owner = {transcend},
   posted-at = {2012-11-05 09:06:46},
   priority = {2},
-  timestamp = {2012.11.08},
   url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.9400}
 }
 
   title = {An investigation of manifold learning for speech analysis},
   booktitle = {Proceedings of the International Conference on Spoken Language Processing},
   year = {2006},
-  pages = {2506--2509}
+  pages = {2506--2509},
+  abstract = {Due to the physiological constraints of articulatory motion the speech
+	apparatus has limited degrees of freedom. As a result, the range
+	of speech sounds a human is capable of producing may lie on a low
+	dimensional submanifold of the high dimensional space of all possible
+	sounds. In this study a number of manifold learning algorithms are
+	applied to speech data in an effort to extract useful low dimensional
+	structure from the high dimensional speech signal. The ability of
+	these manifold learning algorithms to separate vowels in a low dimensional
+	space is evaluated and compared to a classical linear dimensionality
+	reduction method. Results indicate that manifold learning algorithms
+	outperform classical methods in low dimensions and are capable of
+	discovering useful manifold structure in speech data.}
 }
 
 @INPROCEEDINGS{Errity2007a,
   timestamp = {2012.11.08}
 }
 
+@INPROCEEDINGS{hegde2004cluster,
+  author = {Hegde, R. and Murthy, H.},
+  title = {Cluster and intrinsic dimensionality analysis of the modified group
+	delay feature for speaker classification},
+  booktitle = {Neural Information Processing},
+  year = {2004},
+  pages = {1172--1178},
+  organization = {Springer},
+  abstract = {Speakers are generally identified by using features derived from the
+	Fourier transform magnitude. The Modified group delay feature(MODGDF)
+	derived from the Fourier transform phase has been used effectively
+	for speaker recognition in our previous efforts.Although the efficacy
+	of the MODGDF as an alternative to the MFCC is yet to be established,
+	it has been shown in our earlier work that composite features derived
+	from the MFCC and MODGDF perform extremely well. In this paper we
+	investigate the cluster structures of speakers derived using the
+	MODGDF in the lower dimensional feature space. Three non linear dimensionality
+	reduction techniques The Sammon mapping, ISOMAP and LLE are used
+	to visualize speaker clusters in the lower dimensional feature space.
+	We identify the intrinsic dimensionality of both the MODGDF and MFCC
+	using the Elbow technique. We also present the results of speaker
+	identification experiments performed using MODGDF, MFCC and composite
+	features derived from the MODGDF and MFCC.}
+}
+
 @ARTICLE{Hermansky1985,
   author = {Hermansky, H. and Hanson, B.A. and Wakita, H.},
   title = {Low-dimensional representation of vowels based on all-pole modeling
   publisher = {Elsevier}
 }
 
-@ARTICLE{Huh2012,
-  author = {Huh, S. and Fienberg, S.E.},
-  title = {Discriminative topic modeling based on manifold learning},
-  journal = {ACM Transactions on Knowledge Discovery from Data (TKDD)},
-  year = {2012},
-  volume = {5},
-  pages = {20},
-  number = {4},
-  publisher = {ACM}
-}
-
 @ARTICLE{Jansen2009,
   author = {Jansen, Aren and Niyogi, Partha},
   title = {{Point process models for spotting keywords in continuous speech}},

bib/etale_speech_perception.bib

 % This file was created with JabRef 2.7b.
 % Encoding: UTF-8
 
+@ARTICLE{browman1992articulatory,
+  author = {Browman, C.P. and Goldstein, L. and others},
+  title = {Articulatory phonology: An overview},
+  journal = {Phonetica},
+  year = {1992},
+  volume = {49},
+  pages = {155--180},
+  number = {3-4},
+  comment = {Gestural model of speech perception}
+}
+
+@ARTICLE{diehl1989objects,
+  author = {Diehl, R.L. and Kluender, K.R.},
+  title = {On the objects of speech perception},
+  journal = {Ecological Psychology},
+  year = {1989},
+  volume = {1},
+  pages = {121--144},
+  number = {2},
+  abstract = {From both direct-realist and motor-theoretic perspectives, the objects
+	of speech perception are construed as articulatory events. We offer
+	the alternative view that it is the auditory properties of phonetic
+	events to which listeners are primarily sensitive. Evidence for this
+	alternative view comes from a variety of sources, including studies
+	of phonetic and phonological universals, comparisons of the perception
+	of speech and nonspeech signals, cross-language perceptual experiments,
+	and studies of phonetic categorization by nonhuman animals.},
+  comment = {Auditory enhancement hypothesis},
+  publisher = {Taylor \& Francis}
+}
+
+@ARTICLE{fowler1986event,
+  author = {Fowler, C.A.},
+  title = {An event approach to the study of speech perception from a direct-realist
+	perspective},
+  journal = {Journal of Phonetics},
+  year = {1986},
+  volume = {14},
+  pages = {3--28},
+  number = {1},
+  comment = {Direct-realist theory of speech perception}
+}
+
+@ARTICLE{galantucci2006motor,
+  author = {Galantucci, B. and Fowler, C.A. and Turvey, M.T.},
+  title = {The motor theory of speech perception reviewed},
+  journal = {Psychonomic bulletin \& review},
+  year = {2006},
+  volume = {13},
+  pages = {361--377},
+  number = {3},
+  publisher = {Springer}
+}
+
+@ARTICLE{liberman1957some,
+  author = {Liberman, A.M.},
+  title = {Some results of research on speech perception},
+  journal = {The Journal of the Acoustical Society of America},
+  year = {1957},
+  volume = {29},
+  pages = {117--123},
+  number = {1},
+  publisher = {Acoustical Society of America}
+}
+
+@ARTICLE{liberman1967perception,
+  author = {Liberman, A.M. and Cooper, F.S. and Shankweiler, D.P. and Studdert-Kennedy,
+	M.},
+  title = {Perception of the speech code.},
+  journal = {Psychological review},
+  year = {1967},
+  volume = {74},
+  pages = {431},
+  number = {6},
+  comment = {Motor Theory of Speech Perception},
+  publisher = {American Psychological Association}
+}
+
+@ARTICLE{liberman1985motor,
+  author = {Liberman, A.M. and Mattingly, I.G.},
+  title = {The motor theory of speech perception revised},
+  journal = {Cognition},
+  year = {1985},
+  volume = {21},
+  pages = {1--36},
+  number = {1},
+  publisher = {Elsevier}
+}
+
+@ARTICLE{liberman2000relation,
+  author = {Liberman, A.M. and Whalen, D.H.},
+  title = {On the relation of speech to language},
+  journal = {Trends in cognitive sciences},
+  year = {2000},
+  volume = {4},
+  pages = {187--196},
+  number = {5},
+  publisher = {Elsevier}
+}
+
+@ARTICLE{mcgurk1976hearing,
+  author = {McGurk, H. and MacDonald, J.},
+  title = {Hearing lips and seeing voices},
+  year = {1976},
+  abstract = {MOST verbal communication occurs in contexts where the listener can
+	see the speaker as well as hear him. However, speech perception is
+	normally regarded as a purely auditory process. The study reported
+	here demonstrates a previously unrecognised influence of vision upon
+	speech perception. It stems from an observation that, on being shown
+	a film of a young woman's talking head, in which repeated utterances
+	of the syllable [ba] had been dubbed on to lip movements for [ga],
+	normal adults reported hearing [da]. With the reverse dubbing process,
+	a majority reported hearing [bagba] or [gaba]. When these subjects
+	listened to the soundtrack from the film, without visual input, or
+	when they watched untreated film, they reported the syllables accurately
+	as repetitions of [ba] or [ga]. Subsequent replications confirm the
+	reliability of these findings; they have important implications for
+	the understanding of speech perception.},
+  comment = {McGurk effect},
+  publisher = {Nature Publishing Group}
+}
+
 @ARTICLE{nearey1989static,
   author = {Nearey, T.M.},
   title = {Static, dynamic, and relational properties in vowel perception},
   pages = {2088}
 }
 
+@ARTICLE{studdert1970hemispheric,
+  author = {Studdert-Kennedy, M. and Shankweiler, D.},
+  title = {Hemispheric specialization for speech perception},
+  journal = {The Journal of the Acoustical Society of America},
+  year = {1970},
+  volume = {48},
+  pages = {579--594},
+  number = {2B},
+  publisher = {Acoustical Society of America}
+}
+
 @comment{jabref-meta: selector_publisher:}
 
 @comment{jabref-meta: selector_author:}

bib/nlp_manifold_learning_misc.bib

+% This file was created with JabRef 2.7b.
+% Encoding: UTF-8
+
+@ARTICLE{Huh2012,
+  author = {Huh, S. and Fienberg, S.E.},
+  title = {Discriminative topic modeling based on manifold learning},
+  journal = {ACM Transactions on Knowledge Discovery from Data (TKDD)},
+  year = {2012},
+  volume = {5},
+  pages = {20},
+  number = {4},
+  publisher = {ACM}
+}
+
+@comment{jabref-meta: selector_publisher:}
+
+@comment{jabref-meta: selector_author:}
+
+@comment{jabref-meta: selector_journal:}
+
+@comment{jabref-meta: selector_keywords:}
+
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.