Generate QR code
Open Access
Subscription Access
Improving the method for measuring the accuracy indicator of the speech signal autoregressive model
https://doi.org/10.32446/0368-1025it.2022-10-58-63
Abstract
The problem of determining the accuracy of an autoregressive model of a speech signal is considered, and a method for measuring the accuracy index in the sliding observation window mode is proposed. As an indicator of the accuracy of the autoregressive model, a modified value of the COSH-distance (functions of the hyperbolic cosine) relative to the eponymous (one-phoneme) Schuster periodogram was used as a reference spectral sample. To study the possibilities of the proposed method, a full-scale experiment was set up and carried out, in which the object of study was a set of autoregressive models of different orders. These models were obtained by Berg's method for the vowel sounds of the controlled speaker's speech. According to the results of the measurements for each vowel, the optimal values of the autoregressive order and the corresponding optimal autoregressive model were found. It is shown that this optimization made it possible to increase the accuracy of the autoregressive model of the speech signal by more than 60 %, depending on the sound of the controlled speaker's speech and the characteristics of his vocal tract. The results obtained are intended for use in automatic processing and digital speech transmission systems with radical data compression based on linear prediction coefficients.
About the Author
V. V. Savchenko
National Research University Higher School of Economics
Russian Federation
Russian Federation
Vladimir V. Savchenko
N. Novgorod
References
1. Gibson J., Entropy, 2018, vol. 20, no. 10, 7502018. https://doi.org/10.3390/e20100750
2. Savchenko V. V., Radioelectronics and Communications Systems, 2021, vol. 64, no. 11, pp. 592–603. https://doi.org/10.3103/S0735272721110030
3. Савченко А. В., Савченко В. В. Адаптивный метод измерения частоты основного тона с использованием двухуровневой авторегрессионной модели речевого сигнала // Измерительная техника. 2022. № 6. С. 60–66. https://doi.org/10.32446/0368-1025it.2022-6-60-66 [Savchenko V. V., Savchenko A. V., An adaptive method for measuring the pitch frequency using a two-level autoregressive model of a speech signal, Izmeritel’naya tekhnika, 2022, no. 6, pp. 60–66. (In Russ.)].
4. Jaramillo E., Nielsen J. K., Christensen M. G., 27th European Signal Processing Conference (EUSIPCO), 2019, pp. 1–5. https://doi.org/10.23919/EUSIPCO.2019.8902763
5. Савченко В. В. Исследование стационарности случайных временных рядов с использованием принципа минимума информационного рассогласования // Известия вузов. Радиофизика. 2017. Т. 60. № 1. С. 89–96. [Savchenko V. V., Radiophysics and Quantum Electronics, 2017, vol. 60, no. 1, pp. 89–96. https://doi.org/10.1007/s11141-017-9778-y].
6. Cui S., Li E., Kang X., IEEE International Conference on Multimedia and Expo (ICME), London, United Kingdom, 2020, pp. 1–6. https://doi.org/10.1109/ICME46284.2020.9102765
7. Ando Sh., The Journal of the Acoustical Society of America, 2019, vol. 146, no. 11, 2846. https://doi.org/10.1121/1.5136873
8. Savchenko V. V., Savchenko А. V., Radioelectronics and Communications Systems, 2019, vol. 62, no. 5, pp. 276–286. https://doi.org/10.3103/S0735272719050042
9. Ding J., Tarokh V., Yang Y., IEEE Transactions on Information Theory, 2018, vol. 64, no. 6, pp. 4024–4043. https://doi.org/10.1109/TIT.2017.2717599
10. Savchenko V. V., Radioelectronics and Communications Systems, 2020, vol. 63, pp. 532–542. https://doi.org/10.3103/S0735272720100039
11. Савченко В. В., Савченко Л. В. Метод измерений показателя разборчивости речевого сигнала в информационной метрике Кульбака-Лейблера // Измерительная техника. 2019. № 9. С. 59–64. https://doi.org/10.32446/0368-1025it.2019-9-59-64 [Savchenko V. V., Savchenko L. V., Measurement Techniques, 2019, vol. 62, no. 9, рр. 832–839. https://doi.org/10.1007/s11018-019-01702-1].
12. Tohyama M., Spectral envelope and source signature analysis, in: Acoustic Signals and Hearing, Academic Press, 2020, pp. 89–110. https://doi.org/10.1016/B978-0-12-816391-7.00013-9
13. Sun P., Mahdi A., Xu J., Qin J., Speech Communication, 2018, vol. 101, pp. 57–69. https://doi.org/10.1016/j.specom.2018.05.006
14. Савченко В. В., Савченко Л. В. Метод авторегрессионного моделирования речевого сигнала на основе его дискретного фурье-преобразования и масштабно-инвариантной меры информационного рассогласования // Радиотехника и электроника. 2021. Т. 66. № 11. С. 1100-1108. https://doi.org/10.31857/S0033849421110085 [Savchenko V. V., Savchenko L. V., Journal of Communications Technology and Electronics, 2021, vol. 66, no. 11, pp. 1266–1273. https://doi.org/10.1134/s1064226921110085].
15. Marple S. L., Digital spectral analysis with applications, 2nd ed., Mineola, New York, Dover Publications, 2019, 432 p.
16. Радиоэлектронные системы. Основы построения и теория: Справочник / Под ред. Я. Д. Ширмана. Изд. 2-е, перераб. и доп. М.: Радиотехника, 2007, 657 c. [Radioelektronnye sistemy. Osnovy postroeniya i teoriya: Spravochnik, Ed. Ya. D. Shirman, 2nd ed., Moscow, Radiotekhnika Publ., 2007, 657 c. (In Russ.)].
17. Benesty J., Chen J., Huang Y., Linear Prediction, in: Springer handbook of speech processing, Part B, N.Y., Springer, 2008, pp. 111–124. https://doi.org/10.1007/978-3-540-49127-9_7
18. Palaparthi A., Titze I. R., Speech Communication, 2020, vol. 123, pp. 98–108. https://doi.org/10.1016/j.specom.2020.07.003
19. Rabiner L. R., Shafer R. W., Theory and Applications of Digital Speech Processing, Boston, Pearson, 2010, 1060 p.
20. Savchenko A. V., Savchenko V. V., Savchenko L. V., Optimization Letters, 2021, no. 7. https://doi.org/10.1007/s11590-021-01790-5
21. Kumar S., Singh S. K., Bhattacharya S., International Journal of Speech Technology, 2015, vol. 18, pp. 521–527. https://doi.org/10.1007/s10772-015-9296-2
Review
For citations:
Savchenko V.V. Improving the method for measuring the accuracy indicator of the speech signal autoregressive model. Izmeritel`naya Tekhnika. 2022;(10):58-63. (In Russ.) https://doi.org/10.32446/0368-1025it.2022-10-58-63
Views:
94
Email this article 