This paper shows that machine learning techniques are very successful at classifying the Russian voiceless non-palatalized fricatives [f], [s], and [ʃ] using a small set of acoustic cues. From a data sample of 6320 tokens of read sentences produced by 40 participants, temporal and spectral measurements are extracted from the full sound, the noise duration, and the middle 30 ms windows. Furthermore, 13 mel-frequency cepstral coefficients (MFCCs) are computed from the middle 30 ms window. Classifiers based on single decision trees, random forests, support vector machines, and neural networks are trained and tested to distinguish between these three fricatives. The results demonstrate that, first, the three acoustic cue extraction techniques are similar in terms of classification accuracy (93% and 99%) but that the spectral measurements extracted from the full frication noise duration result in slightly better accuracy. Second, the center of gravity and the spectral spread are sufficient for the classification of [f], [s], and [ʃ] irrespective of contextual and speaker variation. Third, MFCCs show a marginally higher predictive power over spectral cues (<2%). This suggests that both sets of measures provide sufficient information for the classification of these fricatives and their choice depends on the particular research question or application.
References
1.
Anjos
, I.
, Eskenazi
, M.
, Marques
, N.
, Grilo
, M.
, Guimarães
, I.
, Magalhães
, J.
, and Cavaco
, S.
(2020
). “Detection of voicing and place of articulation of fricatives with deep learning in a virtual speech and language therapy tutor
,” in Proceedings of Interspeech 2020
, October 25–29, Shanghai, China, pp. 3156
–3160
.2.
Behrens
, S. J.
, and Blumstein
, S. E.
(1988
). “Acoustic characteristics of English voiceless fricatives: A descriptive analysis
,” J. Phon.
16
(3
), 295
–298
.3.
Blumstein
, S. E.
, and Stevens
, K. N.
(1981
). “Phonetic features and acoustic invariance in speech
,” Cognition
10
(1
), 25
–32
.4.
Boersma
, P.
, and Weenink
, D.
(2021
). “Praat: Doing phonetics by computer (version 3.9) [computer program]
,” https://www.fon.hum.uva.nl/praat/ (Last viewed 4/7/2021).5.
Bolla
, K.
(1981
). A conspectus of Russian speech sounds
(Böhlau Verlag
, Vienna, Austria
).6.
Breiman
, L.
(2001
). “Random forests
,” Mach. Learn.
45
(1
), 5
–32
.7.
Breiman
, L.
, Friedman
, J.
, Stone
, C. J.
, and Olshen
, R.
(1984
). Classification and Regression Trees
(Taylor & Francis
, New York
).8.
Catford
, J. C.
(1977
). Fundamental Problems in Phonetics
(Indiana University
, London
).9.
Catford
, J. C.
(1988
). A Practical Introduction to Phonetics
(Oxford University
, London
).10.
de Manrique
, A. M. B.
, and Massone
, M. I.
(1981
). “Acoustic analysis and perception of Spanish fricative consonants
,” J. Acoust. Soc. Am.
69
(4
), 1145
–1153
.11.
Derkach
, M.
, Fant
, G.
, and de Serpa-Leitao
, A.
(1970
). “Phoneme coarticulation in Russian hard and soft VCV-utterances with voiceless fricatives
,” STLQPSR
11
(2–3
), 1
–7
.12.
Dowle
, M.
, and Srinivasan
, A.
(2019
). “data.table: Extension of data.frame
,” R package version 1.12.2, https://CRAN.R-project.org/package=data.table (Last viewed 8/4/2021).13.
Draxler
, C.
, and Jänsch
, K.
(2018
). “SpeechRecorder (version 3.28.0) [computer program]
,” https://www.bas.uni-muenchen.de/Bas/software/speechrecorder/ (Last viewed 12/28/2020).14.
Forrest
, K.
, Weismer
, G.
, Milenkovic
, P.
, and Dougall
, R. N.
(1988
). “Statistical analysis of word-initial voiceless obstruents: Preliminary data
,” J. Acoust. Soc. Am.
84
(1
), 115
–123
.15.
Fritsch
, S.
, Guenther
, F.
, and Wright
, M. N.
(2019
). “neuralnet: Training of neural networks
,” R package version 1.44.2, https://CRAN.R-project.org/package=neuralnet (Last viewed 8/4/2021).16.
Funatsu
, S.
, and Kiritani
, S.
(1998
). “Perceptual properties of Russians with Japanese fricatives
,” in Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP 98)
, November 30-December 4, Sydney, Australia.17.
Ghaffarvand Mokari
, P.
, and Mahdinezhad Sardhaei
, N.
(2020
). “Predictive power of cepstral coefficients and spectral moments in the classification of Azerbaijani fricatives
,” J. Acoust. Soc. Am.
147
(3
), EL228
–EL234
.18.
Gordon
, M.
, Barthmaier
, P.
, and Sands
, K.
(2002
). “A cross-linguistic acoustic study of voiceless fricatives
,” J. Int. Phon. Assoc.
32
(2
), 141
–174
.19.
Haykin
, S.
(1998
). Neural Networks: A Comprehensive Foundation
(Prentice Hall
, Englewood Cliffs, NJ
).20.
Hayward
, K.
(2000
). Longman Linguistics Library Experimental Phonetics
, 2nd ed. (Longman
, New York
).21.
Heinz
, J. M.
, and Stevens
, K. N.
(1961
). “On the properties of voiceless fricative consonants
,” J. Acoust. Soc. Am.
33
(5
), 589
–596
.22.
Hoelterhoff
, J.
, and Reetz
, H.
(2007
). “Acoustic cues discriminating German obstruents in place and manner of articulation
,” J. Acoust. Soc. Am.
121
(2
), 1142
–1156
.23.
Hughes
, G. W.
, and Halle
, M.
(1956
). “Spectral properties of fricative consonants
,” J. Acoust. Soc. Am.
28
(2
), 303
–310
.24.
Jassem
, W.
(1965
). “The formants of fricative consonants
,” Lang. Speech
8
(1
), 1
–16
.25.
Jassem
, W.
(1995
). “The acoustic parameters of Polish voiceless fricatives: An analysis of variance
,” Phonetica
52
(3
), 251
–258
.26.
Jesus
, L. M. T.
, and Jackson
, P. J. B.
(2008
). “Frication and voicing classification
,” in Computational Processing of the Portuguese Language
, edited by A.
Teixeira
, V. L. S.
de Lima
, L. C.
de Oliveira
, and P.
Quaresma
(Springer
, Berlin
), pp. 11
–20
.27.
Jesus
, L. M. T.
, and Shadle
, C. H.
(2002
). “A parametric study of the spectral characteristics of European Portuguese fricatives
,” J. Phon.
30
(3
), 437
–464
.28.
29.
Jongman
, A.
, Wayland
, R.
, and Wong
, S.
(2000
). “Acoustic characteristics of English fricatives
,” J. Acoust. Soc. Am.
108
(3
), 1252
–1263
.30.
Kisler
, T.
, Reichel
, U.
, and Schiel
, F.
(2017
). “Multilingual processing of speech via web services
,” Comput. Speech Lang.
45
, 326
–347
.31.
Kissine
, M.
, Van de Velde
, H.
, and van Hout
, R.
(2003
). “An acoustic study of standard Dutch /v/, /f/, /z/ and /s/
,” Linguist. Netherlands
20
, 93
–104
.32.
Kochetov
, A.
(2017
). “Acoustics of Russian voiceless sibilant fricatives
,” J. Int. Phon. Assoc.
47
(3
), 321
–348
.33.
Kong
, Y.-Y.
, Mullangi
, A.
, and Kokkinakis
, K.
(2014
). “Classification of fricative consonants for speech enhancement in hearing devices
,” PLoS One
9
(4
), e95001
.34.
Kuhn
, M.
, Chow
, F.
, and Wickham
, H.
(2019
). “rsample: General resampling infrastructure
,” R package version 0.0.5, https://CRAN.R-project.org/package=rsample (Last viewed 8/4/2021).35.
Kuhn
, M.
, and Vaughan
, D.
(2019
). “parsnip: A common API to modeling and analysis functions
,” R package version 0.0.3.1, https://CRAN.R-project.org/package=parsnip (Last viewed 8/4/2021).36.
Kuhn
, M.
, and Wickham
, H.
(2019
). “recipes: Preprocessing tools to create design matrices
,” R package version 0.1.6, https://CRAN.R-project.org/package=recipes (Last viewed 8/4/2021).37.
Ladefoged
, P.
, and Maddieson
, I.
(1996
). The Sounds of the World's Languages
(Blackwell
, Oxford, UK
).38.
Ladefoged
, P.
, and Wu
, Z.
(1984
). “Places of articulation: An investigation of Pekingese fricatives and affricates
,” J. Phon.
12
(3
), 267
–278
.39.
Liaw
, A.
, and Wiener
, M.
(2002
). “Classification and regression by randomForest
,” R News
2
(3
), 18
–22
.40.
Maniwa
, K.
, Jongman
, A.
, and Wade
, T.
(2009
). “Acoustic characteristics of clearly spoken English fricatives
,” J. Acoust. Soc. Am.
125
(6
), 3962
–3973
.41.
Mann
, V. A.
, and Repp
, B. H.
(1980
). “Influence of vocalic context on perception of the [ʃ]-[s] distinction
,” Percept. Psychophys.
28
(3
), 213
–228
.42.
McFarland
, D. H.
, Baum
, S. R.
, and Chabot
, C.
(1996
). “Speech compensation to structural modifications of the oral cavity
,” J. Acoust. Soc. Am.
100
(2
), 1093
–1104
.43.
McMurray
, B.
, and Jongman
, A.
(2011
). “What information is necessary for speech categorization? Harnessing variability in the speech signal by integrating cues computed relative to expectations
,” Psychol. Rev.
118
(2
), 219
–246
.44.
Meyer
, D.
, Dimitriadou
, E.
, Hornik
, K.
, Weingessel
, A.
, and Leisch
, F.
(2019
). “e1071: Misc functions of the Department of Statistics, Probability Theory Group (formerly: E1071)
,” R package version 1.7-2, https://CRAN.R-project.org/package=e1071 (Last viewed 8/4/2021).45.
Milborrow
, S.
(2019
). “rpart.plot: Plot rpart models: An enhanced version of plot.rpart
,” R package version 3.0.8, https://CRAN.R-project.org/package=rpart.plot (Last viewed 8/4/2021).46.
Nagamine
, T.
, Seltzer
, M.
, and Mesgarani
, N.
(2015
). “Exploring how deep neural networks form phonemic categories
,” in Proceedings of Interspeech 2015
, September 6–10, Dresden, Germany, pp. 1912
–1916
.47.
Newell
, K. M.
, and Hancock
, P. A.
(1984
). “Forgotten moments
,” J. Mot. Behav.
16
(3
), 320
–335
.48.
Nirgianaki
, E.
(2014
). “Acoustic characteristics of Greek fricatives
,” J. Acoust. Soc. Am.
135
(5
), 2964
–2976
.49.
Nittrouer
, S.
, Studdert-Kennedy
, M.
, and McGowan
, R. S.
(1989
). “The emergence of phonetic segments
,” J. Speech Lang. Hear. Res.
32
(1
), 120
–132
.50.
Padgett
, J.
, and Żygis
, M.
(2007
). “The evolution of sibilants in Polish and Russian
,” J. Slavic Linguist.
15
(2
), 291
–324
.51.
Paluszynska
, A.
, and Biecek
, P.
(2017
). “randomForestExplainer: Explaining and visualizing random forests in terms of variable importance
,” R package version 0.9, https://CRAN.R-project.org/package=randomForestExplainer (Last viewed 8/4/2021).52.
Parks
, R. W.
, Levine
, D. S.
, and Long
, D. L.
(1998
). Computational Neuroscience Fundamentals of Neural Network Modeling: Neuropsychology and Cognitive Neuroscience
(MIT
, Cambridge, MA
).53.
Patil
, V.
, and Rao
, P.
(2008
). “Acoustic cues to manner of articulation of obstruents in Marathi
,” in Proceedings of Frontiers of Research on Speech and Music (FRSM)
, edited by A.
Okrent
and J.
Boyle
, February 20–21, Kolkata, India.54.
Peeters
, G.
(2004
). “A large set of audio features for sound description (similarity and classification) in the CUIDADO project
,” CUIDADO First Project Report (IRCAM
, Paris, France
).55.
Rabha
, S.
, Sarmah
, P.
, and Prasanna
, S. R. M.
(2019
). “Aspiration in fricative and nasal consonants: Properties and detection
,” J. Acoust. Soc. Am.
146
(1
), 614
–625
.56.
Reidy
, P. F.
(2016
). “Spectral dynamics of sibilant fricatives are contrastive and language specific
,” J. Acoust. Soc. Am.
140
(4
), 2518
–2529
.57.
Schiel
, F.
(1999
). “Automatic Phonetic Transcription of Non-Prompted Speech
,” in Proceedings of the 14th International Congress of Phonetic Sciences
, August 1–7, San Francisco, CA.58.
Shadle
, C. H.
(1985
). “The acoustics of fricative consonants
,” Doctoral dissertation, Massachusetts Institute of Technology.
59.
Shadle
, C. H.
(1990
). “Articulatory-acoustic relationships in fricative consonants
,” in Speech Production and Speech Modelling
(Springer
, New York
), pp. 187
–209
.60.
Shadle
, C. H.
, and Mair
, S.
(1996
). “Quantifying spectral characteristics of fricatives
,” in Proceedings of the Fourth International Conference on Spoken Language Processing, ICSLP '96
, October 3–6, Philadelphia, PA, Vol. 3
, pp. 1521
–1524
.61.
Shupljakov
, V.
, Fant
, G.
, and de Serpa-Leitao
, A.
(1968
). “Acoustical features of hard and soft Russian consonants in connected speech: A spectrographic study
,” STL-QPSR
9
(4
), 1
–6
.62.
Skarnitzl
, R.
, and Machač
, P.
(2011
). “Principles of phonetic segmentation
,” Phonetica
68
, 198
–199
.63.
Soli
, S. D.
(1981
). “Second formants in fricatives: Acoustic consequences of fricative-vowel coarticulation
,” J. Acoust. Soc. Am.
70
(4
), 976
–984
.64.
Spinu
, L.
, Kochetov
, A.
, and Lilley
, J.
(2018
). “Acoustic classification of Russian plain and palatalized sibilant fricatives: Spectral vs. cepstral measures
,” Speech Commun.
100
, 41
–45
.65.
Spinu
, L.
, and Lilley
, J.
(2016
). “A comparison of cepstral coefficients and spectral moments in the classification of Romanian fricatives
,” J. Phon.
57
, 40
–58
.66.
67.
Strevens
, P.
(1960
). “Spectra of fricative noise in human speech
,” Lang. Speech
3
(1
), 32
–49
.68.
Tagliamonte
, S. A.
, and Baayen
, H.
(2012
). “Models, forests, and trees of York English: Was/were variation as a case study for statistical practice
,” Lang. Var. Change
24
, 135
–178
.69.
Tang
, Y.
, and Horikoshi
, M.
(2016
). “ggfortify: Unified interface to visualize statistical result of popular R packages
,” R J.
8
(2
), 474
–489
.70.
Therneau
, T.
, and Atkinson
, B.
(2019
). “rpart: Recursive partitioning and regression trees
,” R package version 4.1-15, https://CRAN.R-project.org/package=rpart (Last viewed 8/4/2021).71.
Timberlake
, A.
(2004
). A Reference Grammar of Russian
(Cambridge University
, Cambridge, UK
).72.
Ting
, K. M.
(2010
). “Precision and recall
,” in Encyclopedia of Machine Learning
, edited by C.
Sammut
and G. I.
Webb
(Springer
, Boston, MA
).73.
Tomiak
, G. R.
(1991
). “An acoustic and perceptual analysis of the spectral moments invariant with voiceless fricative obstruents
,” Doctoral dissertation.
74.
Venables
, W. N.
, Ripley
, B. D.
, and Venables
, W. N.
(2002
). Statistics and Computing Modern Applied Statistics with S
, 4th ed. (Springer
, New York
).75.
Vydana
, H. K.
, and Vuppala
, A. K.
(2016
). “Detection of fricatives using S -transform
,” J. Acoust. Soc. Am.
140
(5
), 3896
–3907
.76.
Wickham
, H.
(2017
). “tidyverse: Easily install and load the Tidyverse
,” R package version 1.2.1, https://CRAN.R-project.org/package=tidyverse (Last viewed 8/4/2021).77.
Wickham
, H.
, and Seidel
, D.
(2020
). “scales: Scale functions for visualization
,” R package version 1.1.1, https://CRAN.R-project.org/package=scales (Last viewed 8/4/2021).78.
Zsiga
, E. C.
(2000
). “Phonetic alignment constraints: Consonant overlap and palatalization in English and Russian
,” J. Phon.
28
(1
), 69
–102
.79.
Żygis
, M.
, and Padgett
, J.
(2010
). “A perceptual study of Polish fricatives, and its implications for historical sound change
,” J. Phon.
38
(2
), 207
–226
.© 2021 Acoustical Society of America.
2021
Acoustical Society of America
You do not currently have access to this content.