Software toolkit for testing of speech signals processing systems. Part 1. Simulation of signals and systems
Main Article Content
Abstract
Structure of the software toolkit for the study and optimization of algorithms of correction and coding systems, which are subject of various distortions, such as noise and reverberation disturbance, coding errors is proposed. The first part of this paper is devoted to consideration of toolkit which permit solve such problems as creating of noisy speech corpora and correction of noisy speech signals. The analysis of advantages and lacks of toolkits FaNT and VoiceBox is made, the guidelines on compensation of the lacks by Matlab resources are developed. The expediency of creation of generalized toolkit, by association of toolkits FaNT and VoiceBox, is shown. Besides the expediency of addition of such toolkit by program modules ensuring simulation of quality estimation of speech processing systems is shown. The examples show efficiency and proper functioning of the proposed toolkit.
Reference 18, figures 5, tables 1.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Beerends J.G. Extension of ITU-T Recommendation P.862 PESQ towards Measuring Speech Intelligibility with Vocoders / Beerends J.G., van Wijngaarden S., van Buuren R. // [On-line]. – Available: http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA454414 (Eng) (1.03.2013).
Cappe O. (2007), [Elimination of the Musical Noise Phenomenon with the Ephraim and Malah Noise Suppressor]. EEE Trans Speech Audio Processing. Vol. 2. No 2. Pp. 345–349.
Erkelens J., Jensen J., Heusdens R. (2007), [A Data-Driven Approach to Optimizing Spectral Speech Enhancement Methods for Various Error Criteria]. Speech Communication. No 49. Pp. 530–541.
Ephraim Y., Malah D. (1984), [Speech Enhancement Using a Minimum-Mean Square Error Short-Time Spectral Amplitude Estimator]. IEEE Trans Acoustics Speech and Signal Proc. Vol. 32. No. 6. Pp. 1109–1121.
Ephraim Y., Malah D. (1985), [Speech Enhancement Using a Minimum Mean-Square Error log-Spectral Amplitude Estimator]. IEEE Trans Acoustics Speech and Signal Proc. Vol. 33. No 2. Pp. 443–445.
Gerkmann T., Hendriks R. (2012), [Unbiased MMSE-Based Noise Power Estimation With Low Complexity and Low Tracking Delay]. IEEE Trans Audio, Speech, Language Proc. No 20. Pp. 1383–1393.
Hirsch H.-G. FaNT - Filtering and Noise Adding Tool. [On-line]. – Available: http://dnt.kr.hsnr.de/ (1.03.2013).
Hirsch H.-G., Finster H. (2005), [The Simulation of Realistic Acoustic Input Scenarios for Speech Recognition Systems]. 9th European Conf on Speech Communication and Technology. Lisboa, September. Pp. 1–4.
Martin R. (2001), [Noise Power Spectral Density Estimation Based on Optimal Smoothing and Minimum Statistics]. IEEE Trans. Speech and Audio Processing. Vol. 9. No 5. Pp. 504–512.
Martin R. (2005), [Statistical Methods for the Enhancement of Noisy Speech. In J. Benesty, S. Makino, and J. Chen, editors, Speech Enhancement, chapter 3]. New-York: Springer-Verlag, Pp. 43–64.
Recommendation ITU-T P.56. Series P: Terminals and Subjective and Objective Assesement Methods. Objective Measuring Apparatus. Objective Measurement of Active Speech Level. – Geneva: Telecommunication Standartisation Sector of ITU, 2008. Vol. 12. P. 24.
Recommendation ITU-T P.863. Series P: Terminals and Subjective and Objective Assesement Methods. Methods for Objective and Subjective Assessment of Speech Quality. Perceptual Objective Listening Quality Assessment. – Geneva: Telecommunication Standartisation Sector of ITU, 2011. Vol. 1. P. 76.
Simulation of Acoustic Environments Including the Transmission over Telephone Channels. [On-line]. – Available: http://dnt.kr.hsnr.de/sireac.html (1.03.2013).
Jacob Benesty, M. Mohan Sondhi, Yiteng Huang. (2008), [Springer Handbook of Speech Processing]. Berlin: Springer-Verlag, P. 1176.
VoiceBox: Speech Processing Toolbox for MATLAB. [On-line]. – Available: http://www.ee.ic.ac.uk/hp/staff/dmb/ (1.03.2013).
Krivnova O.F. (2008), [Speech Corpora on New Technological Way]. Rechevye tehnologii. no2. Pp. 13–23. (Rus)
Prodeus A.N., Didkovskiy V.S., Didkovskaya М.V. (2008), [Acoustic Examination of Speech Communication Channels. Monograph]. Kyiv: Imex-Ltd, P. 420. (Rus)
Prodeus A.N. (2010), [Some Features of the Development of Objective Methods for Speech Intelligibility Measuring]. Electronics and Communications, tematicheskiy vypusk "Electronika i nanotehnologii". Vol. 2. Pp. 217–223. (Rus)
