Abstract
The paper describes a system for automatic evaluation of synthetic speech quality based on continuous detection of emotional states throughout the spoken sentence using a Gaussian mixture model (GMM) classification. The final evaluation decision is made by statistical analysis of the results of emotional class differences between the sentences of original male or female voices and the speech synthesized by various methods with different parameters, approaches to prosody manipulation, etc. The basic experiments confirm the functionality of the developed system producing results comparable with those obtained by the standard listening test method. Additional investigations have shown that a number of mixtures, types of speech features, and a speech database used for creation and training of GMMs have a relatively great influence on continuous emotional style detection and the final quality evaluation of the tested synthetic speech.
This work was supported by the Ministry of Education, Youth and Sports of the Czech Republic, project No. LO1506, and by the Ministry of Education, Science, Research, and Sports of the Slovak Republic VEGA 1/0854/16 (A. Přibilová).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Biagetti, G., Crippa, P., Falaschetti, L., Turchetti, N.: HMM speech synthesis based on MDCT representation. Int. J. Speech Technol. 21(4), 1045–1055 (2018)
Zhao, Y., Takaki, S., Luong, H.T., Yamagishi, J., Saito, D., Minematsu, N.: Wasserstein GAN and waveform loss-based acoustic model training for multi-speaker text-to-speech synthesis systems using a WaveNet vocoder. IEEE Access 6, 60478–60488 (2018)
Saito, Y., Takamichi, S., Saruwatari, H.: Statistical parametric speech synthesis incorporating generative adversarial networks. IEEE/ACM Trans. Audio Speech Lang. Process. 26(1), 84–96 (2018)
Vít, J., Matoušek, J.: Unit-selection speech synthesis adjustments for audiobook-based voices. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2016. LNCS (LNAI), vol. 9924, pp. 335–342. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45510-5_38
Tihelka, D., Grůber, M., Hanzlíček, Z.: Robust methodology for TTS enhancement evaluation. In: Habernal, I., Matoušek, V. (eds.) TSD 2013. LNCS (LNAI), vol. 8082, pp. 442–449. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40585-3_56
Adiga, N., Khonglah, B.K., Prasanna, S.R.M.: Improved voicing decision using glottal activity features for statistical parametric speech synthesis. Digital Signal Process. 71, 131–143 (2017)
Achanta, S., Gangashetty, S.V.: Deep Elman recurrent neural networks for statistical parametric speech synthesis. Speech Commun. 93, 31–42 (2017)
Pal, M., Paul, D., Saha, G.: Synthetic speech detection using fundamental frequency variation and spectral features. Comput. Speech Lang. 48, 31–50 (2018)
Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Process. 3, 72–83 (1995)
Tihelka, D., Hanzlíček, Z., Jůzová, M., Vít, J., Matoušek, J., Grůber, M.: Current state of text-to-speech system ARTIC: a decade of research on the field of speech technologies. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 369–378. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00794-2_40
Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., Weiss, B.: A database of german emotional speech. In: Proceedings of INTERSPEECH 2005, ISCA, Lisbon, Portugal, pp. 1517–1520 (2005)
Přibil, J., Přibilová, A.: Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech. EURASIP J. Audio Speech Music Process. 2013, 8 (2013)
Busso, C., Parthasarathy, S., Burmania, A., AbdelWahab, M., Sadoughi, N., Provost, E.M.: MSP-IMPROV: an acted corpus of dyadic interactions to study emotion perception. IEEE Trans. Affect. Comput. 8(1), 67–80 (2017)
Rencher, A.C., Schaalje, G.B.: Linear Models in Statistics, 2nd edn. Wiley, Hoboken (2008)
Jokinen, E., Saeidi, R., Kinnunen, T., Alku, P.: Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task. Comput. Speech Lang. 53, 1–11 (2019)
Přibil, J., Přibilová, A., Matoušek, J.: Automatic text-independent artifact detection, localization, and classification in the synthetic speech. Radioengineering 26(4), 1151–1160 (2017)
Jůzová, M., Tihelka, D., Skarnitzl, R.: Last syllable unit penalization in unit selection TTS. In: Ekštein, K., Matoušek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 317–325. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-64206-2_36
Nabney, I.T.: Netlab Pattern Analysis Toolbox, Release 3.3. http://www.aston.ac.uk/eas/research/groups/ncrg/resources/netlab/downloads. Accessed 2 Oct 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Přibil, J., Přibilová, A., Matoušek, J. (2019). Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States. In: Ekštein, K. (eds) Text, Speech, and Dialogue. TSD 2019. Lecture Notes in Computer Science(), vol 11697. Springer, Cham. https://doi.org/10.1007/978-3-030-27947-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-27947-9_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27946-2
Online ISBN: 978-3-030-27947-9
eBook Packages: Computer ScienceComputer Science (R0)