Автоматизоване суб'єктивне оцінювання розбірливості мови при різних способах прослуховування

Arkadii Mykolaiovych Prodeus; Kseniia Victorivna Bukhta; Pavlo Vadymovych Morozko; Oleksii Volodymyroych Serhiienko; Ihor Valeriiovych Kotvytskyi; Oleksandr Oleksandrovych Dvornyk

doi:10.20535/2523-4455.2018.23.3.130367

Vol. 23 · Issue 3 · 2018 Jun 30, 2018 Acoustical devices and systems

Automated Subjective Assessment of Speech Intelligibility in Various Listening Modes

Arkadii Mykolaiovych Prodeus Corresponding Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Kseniia Victorivna Bukhta Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Pavlo Vadymovych Morozko Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Oleksii Volodymyroych Serhiienko Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Ihor Valeriiovych Kotvytskyi Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Oleksandr Oleksandrovych Dvornyk Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Pages49-57 PublishedJun 30, 2018

PDF (Ukrainian)

VOL 23 · ISS 3 · 2018 View issue

Abstract

In this paper, the results of automated subjective assessment of Ukrainian speech intelligibility are presented. Speech monosyllables of the consonant-vowel-consonant (CVC) type were listened in two modes: through headphones and through acoustic monitors. The assessment was carried out with the help of specially developed software that allowed automating of articulation tests. Speech listening was done for four situations: pure language; speech distorted by noise; speech distorted by reverberation; speech distorted by the combined effect of noise and reverberation. In the first case, speech monosyllables of 3 articulation tables were listened, each of which contained 50 monosyllables. In the second case, speech distorted by the additive noise with the signal-to-noise ratios (SNR) varied in the range ‑15…+10 dB was listened. In this case, models of white, pink and brown noises were used, the masking properties of which are rather well-studied. In the third case, the reverberant speech for reverberation times in the range 0.3…2.7 s was modeled by convolution of pure speech signals with room impulse responces (RIRs) of various rooms, and in the fourth case the joint action of pink noise and reverberation was considered. It turned out that the masking ability of white noise exceeds one for brown noise for SNR less than minus 5 dB, which is not entirely consistent with preliminary predictive estimates. In addition, it turned out that listening to speech distorted by noise through acoustic monitors could lead to a significant increase in the speech intelligibility, compared to the case of listening through headphones. The analysis of possible causes of abnormal increase in speech intelligibility has been carried out. Early reflections, presence of two loudspeakers, binaural listening, psychophysical features of listeners, as well as peculiarities of software and articulatory testing organization were considered as possible reasons of the phenomenon. After correction of the software and some features of articulation tests it turned out that the results of the speech intelligibility estimation almost coincide when listening to the signals through the headphones and through acoustic monitors, if the distance between the listener and acoustic monitors does not exceed 0.6-0.8 meters. At the same time, these corrections did not differ in the behavior of the dependencies of speech intelligibility on the SNR for small (less minus 5 dB) SNR values The general conclusion may be that listening to speech signals distorted by noise and reverberation interferences, performed with the application of the proposed automated system of articulation tests, indicates the performance and high quality of the developed system. Ref. 13, fig. 7.

Keywords

#automation of articulation tests #speech intelligibility #noise interference #reverberation interference #listening mode

References

V. S. Didkovskyi, M. V. Didkovskaya, and A. N. Prodeus, Akusticheskaja ekspertiza kanalov rechevoj kommunikacii. Monografija [Acoustic examination of the channels of speech communication. Monograph], Kyiv: Imex-LTD, 2008. ISBN: 978-966-8861-85-7
A. N. Prodeus, V. S. Didkovskyi, and M. V. Didkovskaya, Akusticheskaya ekspertiza i korrekciya kommunikacionnyh kanalov. [Acoustic examination and correction of communication channels. Monograph], Saarbrucken: LAP LAMBERT Academic Publishing, OmniScriptum GmbH & Co. KG, 2017. ISBN: 978-3-330-04591-0
O. Arkhypova, V. Zhuravlov, and V. Kumeiko, "Artykuliatsiini tablytsi sliv ukrainskoi movy [Articulation tables of words of the Ukrainian language]," vol. 19, no. 2, pp. 13-17, 2009. URL: http://ela.kpi.ua/handle/123456789/9689
A. E. Arhipov, and E. A. Arhipova, "Analiz i obrabotka dannyh artikulyacionnyh ispytanij [Analysis and processing of articulatory test data]," Scientific and Practical Journal "Information Protection", no. 4, pp. 34-42, 2012. URL: http://aprodeus.narod.ru/Teaching/ZAI/Art_2012_Arhipova_Analis_artikul_tabl.pdf
V. G. Mihajlov, "Diagnosticheskie artikulyacionnye tablicy [Diagnostic articulation tables]," Acoustic Journal, vol. 48, no. 5, pp. 705-712, 2002. URL: http://www.akzh.ru/pdf/2002_5_705-712.pdf
"ANG-2200. Acoustic Noise Generator. Owner’s Guide," Research Electronics, Intl. 455 Security Place Algood, TN 38506, USA. [Online]. Available: https://reiusa.net/wp-content/uploads/2017/11/ANG_Manual_revG.pdf
A. M. Prodeus, A. V. Vityk, and D. Yu. Didenko, "Sub’iektyvne otsiniuvannia yakosti ta rozbirlyvosti movlennievykh syhnaliv, spotvorenykh syntezovanymy shumamy [Subjective evaluation of quality and intelligibility of speech distorted by synthesized noise]," Microsystems, Electronics and Acoustics, vol. 22, no. 6, pp. 45-63, 2017. DOI: 10.20535/2523-4455.2017.22.6.101929 .
A. Prodeus, K. Bukhta, P. Morozko, O. Serhiienko, I. Kotvytskyi, and I. Shherbenko, "Automated System for Subjective Evaluation of the Ukrainian Speech Intelligibility," in Proceedings of IEEE 38th International Conference on Electronics and Nanotechnology (ELNANO) , Kyiv, Ukraine, April 24-26, 2018. DOI: 10.1109/TCSET.2018.8336263 .
J. Bradley, H. Sato, M. Picard, "On the importance of early reflections for speech in rooms," Journal of Acoustical Society of America, vol. 113, no. 6, pp. 3233-3244, June 2003. DOI: 10.1121/1.1570439
J. S. Bradley, "Speech intelligibility studies in classrooms," Journal of the Acoustical Society of America, vol. 80, no. 3, pp. 846-854, 1986. DOI: 10.1121/1.393908
W. Yang and J. S. Bradley, "Effects of room acoustics on the intelligibility of speech in classrooms for young children," Journal of the Acoustical Society of America, vol. 125, no. 2, pp. 922-933, 2009. DOI: 10.1121/1.3058900
I. ArweIler, J. Buchholz, and T. Dau, "Speech intelligibility enhancement by early reflections," in Proceedings of 2nd International Symposium on Auditory and Audiological Research (ISAAR 2009) , Elsinore, Denmark, August 2009. URL: http://orbit.dtu.dk/en/publications/speech-intelligibility-enhancement-by-early-reflections(368caba2-dca2-461f-bc45-d8615f1dd675).html
Yu. K. Makarov, and A. A. Horev, "K ocenke effektivnosti zashity akusticheskoj (rechevoj) informacii [To assess the effectiveness of protection of acoustic (speech) information]," Information Security, no. 4, 2005. URL: http://www.vrsystems.ru/stati/k_ocenke_effektivnosti_zashiti_akusticheskoi_(rechevoi)_informacii.htm