Skip to main content
Erschienen in: Automatic Documentation and Mathematical Linguistics 4/2023

01.08.2023 | AUTOMATION TEXT PROCESSING

Method of Modeling and Harmonic Synthesis of Phonemes of Human Speech with Emotional Coloring

verfasst von: G. Lan, A. S. Fadeev

Erschienen in: Automatic Documentation and Mathematical Linguistics | Ausgabe 4/2023

Einloggen, um Zugang zu erhalten

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Text-to-speech synthesis technology is one of the most important elements in the field of working with human speech. This paper makes an introductory analysis of speaker’s speech sets recorded with different emotional coloration. That enables the identification of patterns in the frequency dynamics of harmonics and the development of a method for the analytical description of the emotional coloration of speech. We propose a model that describes changes in frequency in the vowels and phonemes pronounced with an emotional connotation. The model is based on the use of sigmoid functions and the results of a technique that allows the synthesis of the signal of emotionally colored phonemes.
Literatur
1.
Zurück zum Zitat Li, X., Xu, Y., Zhang, X., et al., Analysis of the research progress in speech emotion recognition, Mod. Comput., 2020, vol. 20, pp. 44–47. Li, X., Xu, Y., Zhang, X., et al., Analysis of the research progress in speech emotion recognition, Mod. Comput., 2020, vol. 20, pp. 44–47.
2.
Zurück zum Zitat Su, Z., Affective speech synthesis, PhD Dissertation, Univ. of Science and Technology of China, 2006. Su, Z., Affective speech synthesis, PhD Dissertation, Univ. of Science and Technology of China, 2006.
3.
Zurück zum Zitat Li, H., Research on speech emotion recognition based on feature selection and optimization, PhD Dissertation, Xidian Univ., 2019. Li, H., Research on speech emotion recognition based on feature selection and optimization, PhD Dissertation, Xidian Univ., 2019.
4.
Zurück zum Zitat Guo, Y., Fu, J., and He, F., Research and design of emotion recognition circuit based on speech affective computing, Mod. Electron. Technique, 2019, vol. 42, no. 22, p. 68. Guo, Y., Fu, J., and He, F., Research and design of emotion recognition circuit based on speech affective computing, Mod. Electron. Technique, 2019, vol. 42, no. 22, p. 68.
5.
Zurück zum Zitat Li, J., Research on dimensional emotion recognition based on speech signal, PhD Dissertation, Tianjin Normal Univ., 2016, p. 48. Li, J., Research on dimensional emotion recognition based on speech signal, PhD Dissertation, Tianjin Normal Univ., 2016, p. 48.
6.
Zurück zum Zitat Li, Y., Wei, D., and Wang, L., Emotional speech synthesis method based on PSOLA and DCT, Comput. Eng., 2017, vol. 12, pp. 284–288. Li, Y., Wei, D., and Wang, L., Emotional speech synthesis method based on PSOLA and DCT, Comput. Eng., 2017, vol. 12, pp. 284–288.
7.
Zurück zum Zitat Li, B., Study on speech synthesis of neurocomputational model for emotional speech, PhD Dissertation, Tianjin Univ., 2016. Li, B., Study on speech synthesis of neurocomputational model for emotional speech, PhD Dissertation, Tianjin Univ., 2016.
8.
Zurück zum Zitat Han, J., Zhang, L., and Zheng, T., Speech Signal Processing, Tsinghua Univ. Press, 2013. Han, J., Zhang, L., and Zheng, T., Speech Signal Processing, Tsinghua Univ. Press, 2013.
9.
Zurück zum Zitat Lan, G. and Morgunov, A., Method for reconstructing human voice phonemes, Vestn. Sovrem. Issled., 2018, no. 10, pp. 130–135. Lan, G. and Morgunov, A., Method for reconstructing human voice phonemes, Vestn. Sovrem. Issled., 2018, no. 10, pp. 130–135.
10.
Zurück zum Zitat Sigmoid function, Wikipedia. https://en.wikipedia.org/ wiki/Sigmoid_function. Cited November 1, 2021. Sigmoid function, Wikipedia. https://​en.​wikipedia.​org/​ wiki/Sigmoid_function. Cited November 1, 2021.
11.
Zurück zum Zitat Ivanov, A.V., Trushin, V.A., and Markelova, G.V., Research on the spectrum of forced speech formants, Nauchn. Vestn. Novosibirsk. Gos. Tekh. Univ., 2015, vol. 61, no. 4, pp. 63–73. Ivanov, A.V., Trushin, V.A., and Markelova, G.V., Research on the spectrum of forced speech formants, Nauchn. Vestn. Novosibirsk. Gos. Tekh. Univ., 2015, vol. 61, no. 4, pp. 63–73.
12.
Zurück zum Zitat Bondarenko, V.P. and Bondar, V.A., Measurement of some characteristics of vowel sounds, Izv. Tomsk. Politekh. Univ., Inzhiniring Gosresursov, 1974, vol. 246, pp. 39–41. Bondarenko, V.P. and Bondar, V.A., Measurement of some characteristics of vowel sounds, Izv. Tomsk. Politekh. Univ., Inzhiniring Gosresursov, 1974, vol. 246, pp. 39–41.
13.
Zurück zum Zitat Volkovets, A.I., Sozdanie i obrabotka zvuka pri razrabotke interaktivnykh prilozhenii (Sound Creation and Processing in the Development of Interactive Applications), Minsk: Belorusskii Gos. Univ. Inf. Radioelektron., 2017. Volkovets, A.I., Sozdanie i obrabotka zvuka pri razrabotke interaktivnykh prilozhenii (Sound Creation and Processing in the Development of Interactive Applications), Minsk: Belorusskii Gos. Univ. Inf. Radioelektron., 2017.
Metadaten
Titel
Method of Modeling and Harmonic Synthesis of Phonemes of Human Speech with Emotional Coloring
verfasst von
G. Lan
A. S. Fadeev
Publikationsdatum
01.08.2023
Verlag
Pleiades Publishing
Erschienen in
Automatic Documentation and Mathematical Linguistics / Ausgabe 4/2023
Print ISSN: 0005-1055
Elektronische ISSN: 1934-8371
DOI
https://doi.org/10.3103/S0005105523040040

Weitere Artikel der Ausgabe 4/2023

Automatic Documentation and Mathematical Linguistics 4/2023 Zur Ausgabe