Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Eurasip Journal on Audio, Speech, and Music Processing

Volumn 2013, Issue 1, 2013, Pages

  Přibil, Jiří ^a   Přibilová, Anna ^b  

^a INSTITUTE OF MEASUREMENT SCIENCE   (Slovakia)

^b SLOVAK UNIVERSITY OF TECHNOLOGY   (Slovakia)

Author keywords

emotional speech recognition; GMM classifier; spectral and prosodic features of speech

Indexed keywords

CLASSIFICATION PROCESS; COMPARATIVE EXPERIMENTS; COMPUTATION COMPLEXITY; EMOTION CLASSIFICATION; EMOTIONAL SPEECH RECOGNITION; GAUSSIAN MIXTURE MODEL; PROSODIC FEATURES; SETTING OF PARAMETERS;

CLASSIFICATION (OF INFORMATION); SOCIAL SCIENCES; SPEECH ANALYSIS; SPEECH PROCESSING; SPEECH RECOGNITION; SPEECH SYNTHESIS;

QUALITY CONTROL;

EID: 84887051130     PISSN: 16874714     EISSN: 16874722     Source Type: Journal    
DOI: 10.1186/1687-4722-2013-8     Document Type: Article

References (41)

1. Malins JG, Joanisse MF: The roles of tonal and segmental information in Mandarin spoken word recognition: an eyetracking study. J. Mem. Lang. 2010, 62:407-420.
2. Kinnunen T, Saeidi R, Sedlák F, Lee KA, Sandberg J, Hansson-Sandsten M, Li H: Low-variance multitaper MFCC features: a case study in robust speaker verification. IEEE Trans. Audio Speech 2012,20(7) 1990-2001.
3. Koolagudi SG, Nandy S, Rao KS: Spectral features for emotion classification, in Proceedings of IEEE International Advance Computing Conference (IACC '09). Patiala: India; 2009. pp. 1292-1296
4. Zhao X, Shao Y, DeL W: CASA-based robust speaker identification. IEEE Trans. Audio Speech 2012,20(5) 1608-1616.
5. Solera-Ureña R, García-Moral AI, Peláez-Moreno C, Martínez-Ramón M, Díaz-de-María F: Real-time robust automatic speech recognition using compact support vector machines. IEEE Trans. Audio Speech 2012,20(4) 1347-1361.
6. Herre J, Allamanche E, Hellmuth O: Robust matching of audio signals using spectral flatness features. In Proceedings of the 2001 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. New York, USA; 2001:127-130.
7. Madhu N: Note on measures for spectral flatness. Electron. Lett. 2009, 45:1195-1196.
8. Misra H, Ikbal S, Sivadas S, Bourlard H: Multi-resolution spectral entropy feature for robust ASR, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), vol.1. Philadelphia, PA: USA; 2005:253-256.
9. Roh YW, Kim DJ, Lee WS, Hong KS: Novel acoustic features for speech emotion recognition. Sci. China Ser. E: Technol. Sci. 2009,52(7) 1838-1848.
10. Hosseinzadeh D, Krishnan S: On the use of complementary spectral features for speaker recognition. EURASIP J. Adv. Signal Process. 2008,2008(Article ID 258184) 10.
11. Pérez-Espinoza H, Reyes-García CA, Villaseñor-Pineda L: Acoustic feature selection and classification of emotions in speech using a 3D continuous emotion model. Biomed. Signal Process. 2012, 7:79-87.
12. Iriondo I, Planet S, Socoró JC, Martínez E, Alías F, Monzo X: Automatic refinement of an expressive speech corpus assembling subjective perception and automatic classification. Speech Commun. 2009, 51:744-758.
13. Fernandez R, Picard R: Recognizing affect from speech prosody using hierarchical graphical models. Speech Commun. 2011, 53:1088-1103.
14. Tsiakoulis P, Potamianos A, Dimitriadis D: Spectral moment features augmented by low order cepstral coefficients for robust ASR. IEEE Signal Process. Lett. 2010,17(6) 551-554.
15. Nicholson J, Takahashi K, Nakatsu R: Emotion recognition in speech using neural networks. Neural Comput. Appl. 2000,9(4) 290-296.
16. Romport J, Matousek J: Formal prosodic structures and their application in NLP. In Text, Speech and Dialogue 2005, LNCS 3658. Edited by: Matousek V, Mautner P, Pavelka T. Berlin: Springer; 2005:371-378.
17. Nwe TL, Foo SW, De LC: Silva, speech emotion recognition using hidden Markov models. Speech Commun. 2003, 41:603-623.
18. Reynolds DA: Speaker identification and verification using Gaussian mixture speaker models. Speech Commun. 1995, 17:91-108.
19. Yun S, Yoo CD: Loss-scaled large-margin Gaussian mixture models for speech emotion classification. IEEE Trans. Audio Speech 2012,20(2) 585-598.
20. He L, Lech M, Maddage NC, Allen NB: Study of empirical mode decomposition and spectral analysis for stress and emotion classification in natural speech. Biomed. Signal Process. 2011, 6:139-146.
21. Bozkurt E, Erzin E, Erdem ÇE, Erdem AT: Formant position based weighted spectral features for emotion recognition. Speech Commun. 2011, 53:1186-1197.
22. Přibil J, Přibilová A: Application of expressive speech in TTS system with cepstral description. In Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction 2007, LNAI 5042. Edited by: Esposito A, Bourbakis N, Avouris N, Hatrzilygeroudis I. Berlin: Springer; 2008:201-213.
23. Grůber M, Hanzlíček Z: Czech expressive speech synthesis in limited domain comparison of unit selection and HMM-based approaches. In TSD 2012, LNCS 7499. Edited by: Sojka P, Horak A, Kopecek I, Pala K. Berlin: Springer; 2012:656-664.
24. Přibil J, Přibilová A: Czech TTS Engine for BraillePen Device Based on Pocket PC Platform. In Proceedings of the 16th Conference Electronic Speech Signal Processing ESSP 05 joined with the 15th Czech-German Workshop Speech Processing. Prague, Czech Republic; 2005:402-408.
25. Přibil J, Přibilová A: Czech and Slovak speaking voice communicator based on PDA/smartphone device for handicapped people. In Proceedings of the International Conference on Applied Electronics. Plzen, Czech Republic; 2012:219-222.
26. Přibil J, Přibilová A: Spectral properties and prosodic parameters of emotional speech in Czech and Slovak. In Speech and Language Technologies. Edited by: Ipšić I. Rijeka, Croatia: InTech; 2011:175-200.
27. Vích R, Přibil J, Smékal Z: New cepstral zero-pole vocal tract models for TTS synthesis. In Proceedings of IEEE Region 8 EUROCON'2001, vol. 2. Bratislava, Slovakia; 2001:458-462.
28. Ilk HG, Eroǧul O, Satar B, Özkaptan Y: Effects of tonsillectomy on speech spectrum. J. Voice 2002, 16:580-586.
29. Fant G: Speech Acoustics and Phonetics. Dordrecht, The Netherlands: Kluwer Academic Publishers; 2004.
30. Murphy PJ: Periodicity estimation in synthesized phonation signals using cepstral rahmonic peaks. Speech Commun. 2006, 48:1704-1713.
31. Silva DG, Olivera LC, Andrea M: Jitter estimation algorithms for detection of pathological voices. EURASIP J. Adv. Signal Process. 2009,2009(Article ID 567875) 9.
32. Berlin Database of Emotional Speech: Department of Communication Science, Institute for Speech and Communication. Berlin: Technical University; http://pascal.kgw.tu-berlin.de/emodb/, Accessed 13 March 2006
33. Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B: A database of German emotional speech. In Proceedings of Interspeech 2005. Lisbon, Portugal; 2005:1517-1520.
34. Přibil J, Přibilová A: Comparison of complementary spectral features of emotional speech for German, Czech, and Slovak. In Cognitive Behavioural Systems, LNCS 7403. Edited by: Esposito A, Hoffmann R, Hubler S, Wrann B. Heidelberg: Springer; 2012:236-250.
35. Nabney T: Netlab Pattern Analysis Toolbox. http://www.mathworks.com/ %20984%20Q2matlabcentral/fileexchange/2654-netlab, Accessed 16 February 2012
36. Bishop CM, Nabney IT: NETLAB Online Reference Documentation. http://www.fizyka.umk.pl/netlab/, Accessed 16 February 2012
37. Truong KP, Leeuven DA: An 'open-set' detection evaluation methodology for automatic emotion recognition in speech. In ParaLing 2007: Workshop on Paralinguistic Speech - Between Models and Data. Saarbrücken, Germany; 2007:5-10.
38. Bitouk D, Verma R, Nenkova A: Class-level spectral features for emotion recognition. Speech Commun. 2010, 52:613-625.
39. Vondra M, Vích R: Recognition of emotions in German speech using Gaussian mixture models. In Multimodal Signals: Cognitive and Algorithmic Issues, LNAI 5398. Edited by: Esposito A, Hussain A, Marinaro M, Martone R. Berlin: Springer; 2009:256-263.
40. Shami M, Verhelst W: An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech. Speech Commun. 2007, 49:201-212.
41. Kotti M, Paternò F: Speaker-independent emotion recognition exploiting a psychologically inspired binary cascade classification schema. Int. J. Speech Technol. 2012, 15:131-150. http://link.springer.com/article/10.1007/ s10772-012-9127-7#page-1