آشکارسازی آغازه در تکنوازی تار بر پایه انرژی و فرکانس پایه
محورهای موضوعی : مهندسی برق و کامپیوتر
بهراز فرخی
1
*
,
احسان‌اله کبیر
2
1 - دانشگاه تربیت مدرس
2 - دانشگاه تربیت مدرس
کلید واژه: آشکارسازي آغازه, پردازش صوت ساز تار موسیقی ایرانی نت,
چکیده مقاله :
در اين مقاله روشي تازه براي آشکارسازي آغازه در تکنوازي ساز تار ارائه شده است. در تعريف تابع آشکارساز آغازه، از دو ويژگي انرژي و فرکانس پايه استفاده کرده‌ايم که نتيجه آن به کمک يک الگوريتم قله‌ياب سازگار براي آشکارسازي اوليه آغازه‌ها استفاده مي‌شود. با استفاده از يک روش تطبيق کليشه‌اي بهبوديافته، فرکانس‌هاي پايه تعيين شده و از تطبيق زمانی آنها با نتايج اوليه، آشکارسازي نهايي آغازه‌ها انجام مي‌شود. تابع آشکارساز پيشنهادی به دليل استفاده هم‌زمان از دو ويژگي انرژی و فرکانس پايه، قابليت تشخيص نت‌های نرم و سخت را داراست. براي آزمايش، اين سيستم را روي مجموعهاي از قطعات تکنوازي تار با آغازه‌هاي معلوم به کار گرفته و نتايج آن را در مقایسه با روش مبتنی بر ویژگی انرژی و بر اساس ملاک F تحليل کرده‌ايم. نتایج به دست آمده نشان‌دهنده بهبود کارایی سیستم در شناسایی آغازه‌های ساز تار است.
This paper develops a new method of onset detection for the Tar, a traditional Iranian musical instrument. The proposed method is based on both types of pitch and energy features and an adaptive peak picking algorithm is utilized for primary onset detection. An improved template matching method is used to detect fundamental frequencies and finally, onsets are tagged based on primary onsets and fundamental frequencies. This step is especially useful to detect the reaz, repeatedly played notes with the same frequency and short durations. For the evaluation of the method, a data set with predetermined onsets was produced and the results were compared with an energy based method explained in terms of F measure.
[1] P. Marsi, Computer Modelling of Sound for Transcription and Synthesis of Musical Signal, Ph.D. Dissertation, University of Bristol, UK, 1996.
[2] A. Klapuri, "Sound onset detection by applying psychoacoustic knowledge," in IEEE Int. Conf. Acoust., Speech, and Sig. Proc., ICASSP'99, vol. 6, pp. 3089-3092, Phoenix, AZ, USA, 15-19 Mar. 1999.
[3] ب. فرخی و ا. کبير، "آشکارسازی آغازه در تکنوازی تار،" اولين کنفرانس بين‌المللی آکوستیک و ارتعاشات، دانشگاه صنعتي اميرکبير، 8 صص.، 30 آذر/ 1 دي 1390.
[4] B. Thoshkahna and K. R. Ramakrishnan, "A psychoacoustics based sound onset detection algorithm for polyphonic audio," in Proc. Int. Conf. on Signal Processing, ICSP'08, pp. 1424-1427, Beijing , China, 26-29 Oct. 2008.
[5] E. Marchi, G. Ferroni, F. Eyben, S. Squartini, and B. Schuller, "Audio onset detection: a wavelet packet based approach with recurrent neural networks," in Proc. IEEE Int. Joint Conf. on Neural Networks, IJCNN'14, pp. 3585-3591, Beijing, China, 6-8 Jul. 2014.
[6] J. P. Bello and M. Sandler, "Phase-based note onset detection for music signals," in IEEE Int, Conf. Acoustics, Speech, and Signal Processing, ICASSP'03, vol. 5, pp. 441-444, 6-10 Apr. 2003.
[7] J. Bello, C. Duxbury, M. Davies, and M. Sandler, "On the use of phase and energy for musical onset detection in thecomplex domain," in IEEE Sig. Proc. Letters, vol. 11, no. 6, pp. 553-556, Jun. 2004.
[8] S. Dixon, "Onset detection revisited," in Proc. 9th Int. Conf. on Digital Audio Effects, DAFX'06, pp. 133-137, Montreal, Canada, 18-20 Sep. 2006.
[9] R. Zhou, M. Mattavelli, and G. Zoia, "Music onset detection based on resonator time frequency image," IEEE Trans. on Audio, Speech, and Language Processing, vol. 16, no. 8, pp. 1685-1695, Nov. 2008.
[10] N. Collins, "Using a pitch detector as an onset detector," in Proc. Int. Soc. Music Inf. Retrieval Conf., ISMIR'0 , pp. 100-106, London, UK, 11-15 Sep. 2005.
[11] R. Zhou, Feature Extraction of Musical Content for Automatic Music Transcription, Ph.D Dissertation, Swiss Federal Inst. of Technol., Lausanne, Oct. 2006.
[12] H. Heo, D. Sung, and K. Lee, "Note onset detection based on harmonic cepstrum regularity," in Proc, IEEE In. Conf. on Multimedia and Expo., ICME'13, 6 pp., San Jose, CA, Jul. 2013.
[13] پ. جعفرزاده، آوانگاری اصوات موسيقی ايرانی، دانشگاه سمنان، پايان‌نامه کارشناسی ارشد، اسفند 1380.
[14] پ. حيدريان، بازشناسي نت‌هاي موسيقي براي سنتور، پايان‌نامه کارشناسي ارشد، دانشگاه تربيت مدرس، بهار 1379.
[15] J. Bello, et al., "A tutorial on onset detection in musical signals," IEEE Trans. Speech and Audio Processing, vol. 13, no. 5, pp. 1035-1047, Sep. 2005.
[16] N. Collins, "A comparison of sound onset detection algorithms with emphasis on psychoacoustically motivated detection functions," in Proc. 118th AES Conv., Barcelona, Spain, pp. 28-31, May 2005.
[17] A. Holzapfel, Y. Stylianou, A. C. Gedic, and B. Bozkurt, "Three dimensions of pitched instrument onset detection," IEEE Trans. on Audio, Speech, and Language Processing, vol. 18, no. 6, pp. 1517-1527, Aug. 2010.
[18] E. Benetod and Y. Stylianou, "Auditory spectrum-based pitched instrument onset detection," IEEE Trans. on Audio, Speech, and Language Processing, vol. 18, no. 8, pp. 1968-1977, Nov. 2010.
[19] P. M. Kumar, J. Sebastian, and H. A. Murthy, "Musical onset detection on carnatic percussion instruments," in Proc. IEEE 21st National Conf. on Communications, NCC'15, Mumbai, India, 6 pp., 27 Feb.- 1 Mar.. 2015.
[20] H. Thornburg, R. J. Leistikow, and J. Berger, "Melody extraction and musical onset detection via probabilistic models of framewise STFT peak data," IEEE Trans. on Audio, Speech, and Language Processing, vol. 15, no. 4, pp. 1257-1272, May 2007.
[21] N. Degara, M. E. P. Davies, A. Pena, and Mark D. Plumbley, "Onset event decoding exploiting the rhythmic structure of polyphonic music," IEEE J. of Selected Topics in Signal Processing, vol. 5, no. 6, pp. 1228-1239, Oct. 2011.
[22] B. Zhu, J. Gan, J. Cai, Y. Wang, and H. Wang, "Adaptive onset detection based on instrument recognition," in Proc. 12th IEEE Int. Conf. on Signal Processing, ICSP'14, pp. 2416-2421, Hangzhou, China, 19-23 Oct. 2014.
[23] J. C. Brown, "Calculation of a constant Q spectral transform," J. Acoust. Soc. Am., vol. 89, no. 1, pp. 425-434, Jan. 1991.
[24] J. C. Brown and M. S. Puckette, "An efficient algorithm for the calculation of a constant Q transform," J. Acoust. Soc. Am., vol. 92, no. 5, pp. 2698-2701, Nov. 1992.
[25] B. C. J. Moore, B. R. Glasberg, and T. Baer, "A model for the prediction of thresholds, loudness, and partial loudness," J. Audio Eng. Soc., vol. 45, no. 4, pp. 224-240, Apr. 1997.
[26] J. C. Brown, "Musical fundamental frequency tracking using a pattern recognition method," J. Acoust. Soc. Am., vol. 92, no. 3, pp. 1394-1402, Sep. 1992.
[27] تار هوشنگ ظريف، همراهی تنبک سيامک بنايي، انتشارات ماهور، سی‌دی شماره 107.
[28] دستور مقدماتي تار، اجرا هوشنگ ظريف، انتشارات ماهور، سی‌دی شماره 235.
[29] ردیف دوره عالی استاد علی اکبرخان شهنازی، انتشارات ماهور، مجموعه 6کاستی.
[30] "صد سال تار،" انتشارات ماهور، کاست شماره 118.