{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:56:43Z","timestamp":1764997003724},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,6,4]],"date-time":"2014-06-04T00:00:00Z","timestamp":1401840000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s10772-014-9236-6","type":"journal-article","created":{"date-parts":[[2014,6,3]],"date-time":"2014-06-03T07:11:32Z","timestamp":1401779492000},"page":"389-399","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Feature extraction technique using ERB like wavelet sub-band periodic and aperiodic decomposition for TIMIT phoneme recognition"],"prefix":"10.1007","volume":"17","author":[{"given":"Astik","family":"Biswas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. K.","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anirban","family":"Bhowmick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahesh","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,6,4]]},"reference":[{"key":"9236_CR1","doi-asserted-by":"crossref","unstructured":"Adami, A., Burget, L., Duponi, S., Garudadri, H., Grezl, F., Hermansky, H., Jain, P., Kajarekar, S., Morgan, N. & Sivadas, S. (2002). QUALCOMM-ICSI-OGI features for ASR. Proceedings ICSLP. pp 21\u201324.","DOI":"10.21437\/ICSLP.2002-4"},{"key":"9236_CR2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/TSA.2002.800556","volume":"10","author":"AM Ali","year":"2002","unstructured":"Ali, A. M., Spiegel, J. V., & Mueller, P. (2002). Robust auditorybased speech processing using the average localized synchrony detection. IEEE Transactions on Speech and Audio Processing, 10, 279\u2013292.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9236_CR3","unstructured":"Berouti, M., Schwartz, R. & Makhoul, J. (1979). Enhancement of speech corrupted by acoustical noise. Proceedings ICASSP. pp 208\u2013211."},{"key":"9236_CR4","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1016\/j.compeleceng.2014.01.008","volume":"40","author":"A Biswas","year":"2014","unstructured":"Biswas, A., Sahu, P. K., & Chandra, M. (2014). Admissible wavelet packet features based on human inner ear frequency response for Hindi consonant recognition. Computer and Electrical Engineering, 40, 1111\u20131122.","journal-title":"Computer and Electrical Engineering"},{"key":"9236_CR5","doi-asserted-by":"crossref","first-page":"2848","DOI":"10.1121\/1.419476","volume":"101","author":"D Cheveigne\u2019","year":"1997","unstructured":"Cheveigne\u2019, D., McAdams, A., & Marin, S. (1997). Concurrent vowel identification. II. Effects of phase, harmonicity, and task. The Journal of the Acoustical Society of America, 101, 2848\u20132856.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9236_CR6","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis, S. B., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics Speech and Signal Processing ASSP, 28, 357\u2013366.","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing ASSP"},{"key":"9236_CR7","unstructured":"El-Fattah, M.A.A., Dessouky, M.I., Abbas, A.M., Diab, S.M., El-Sayed, M., El-Rabaie, W.A.-N., Alshebeili, S.A., El-samie, F.E.A. (2013). Speech enhancement with an adaptive Wiener filter. Int J Speech Technol, 1\u201312."},{"key":"9236_CR8","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/97.928676","volume":"8","author":"O Farooq","year":"2001","unstructured":"Farooq, O., & Datta, S. (2001). Mel filter-like admissible wavelet packet structure for speech recognition. The IEEE Signal Processing Letters, 8, 196\u2013198.","journal-title":"The IEEE Signal Processing Letters"},{"key":"9236_CR9","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1049\/ip-vis:20040324","volume":"151","author":"O Farooq","year":"2004","unstructured":"Farooq, O., & Datta, S. (2004). Wavelet based robust sub-band features for phoneme recognition. IEE Proceedings-Vision, Image and Signal Processing, 151, 187\u2013193.","journal-title":"IEE Proceedings-Vision, Image and Signal Processing"},{"key":"9236_CR10","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1142\/S0219691310003845","volume":"8","author":"O Farooq","year":"2010","unstructured":"Farooq, O., Datta, S., & Shrotriya, M. C. (2010). Wavelet sub-band based temporal features for robust Hindi phoneme recognition. International Journal of Wavelets, Multiresolution and Information Processing, 8, 847\u2013859.","journal-title":"International Journal of Wavelets, Multiresolution and Information Processing"},{"key":"9236_CR11","doi-asserted-by":"crossref","unstructured":"Gao, Y., Huang, T., Chen, S., Haton, J. (1992). Auditory model based speech processing. Proceedings ICSLP. pp 73\u201376.","DOI":"10.21437\/ICSLP.1992-21"},{"key":"9236_CR12","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G. & Pallett, D.S. (1993). DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1\u20131.1. NASA STI\/Recon Technical Report N, 93, 27403."},{"key":"9236_CR13","volume-title":"Speech processing in the auditory system: an overview","author":"S Greenberg","year":"2004","unstructured":"Greenberg, S., Ainsworth, W. A., Popper, A. N., & Fay, R. R. (2004). Speech processing in the auditory system: an overview. New York: Springer-Verlag."},{"key":"9236_CR14","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky, H. (1990). Perceptual linear predictive (PLP) analysis. Journal of the Acoustical Society of America, 87, 1738\u20131752.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9236_CR15","unstructured":"Hohmann, V. & Kollmeier, B. (2006). A nonlinear auditory filterbank controlled by sub-band instantaneous frequency estimates. Int. Symp. Hear. 2006 (Springer). Cloppenburg, Germany, pp 11\u201318."},{"key":"9236_CR16","doi-asserted-by":"crossref","unstructured":"Ishizuka, K. & Miyazaki, N, (2004). Speech feature extraction method representing periodicity and aperiodicity in sub bands for robust speech recognition. Proceedings ICASSP. pp 141\u2013144.","DOI":"10.1109\/ICASSP.2004.1325942"},{"key":"9236_CR17","doi-asserted-by":"crossref","unstructured":"Ishizuka, K., & Nakatani, T. (2006). A feature extraction method using sub-band based periodicity and aperiodicity decomposition with noise robust frontend processing for automatic speech recognition. Speech Communication, 48, 1447\u20131457.","DOI":"10.1016\/j.specom.2006.06.008"},{"key":"9236_CR18","doi-asserted-by":"crossref","unstructured":"Kajita, S. & Itakura, F. (1995). Robust feature extraction using SBCOR analysis. Proceedings ICASSP. pp 421\u2013424.","DOI":"10.1109\/ICASSP.1995.479611"},{"key":"9236_CR19","unstructured":"Kim, D. S., Lee, S. Y., & Kil, R. M. (1999). Auditory processing of speech signals for robust speech recognition in real-world noisy environments. IEEE Transactions on Speech and Audio Processing, 7, 55\u201369."},{"key":"9236_CR20","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"KF Lee","year":"1989","unstructured":"Lee, K. F., & Hon, H. W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics Speech and Signal Processing, 37, 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"9236_CR21","unstructured":"Li Q., Soong, F.K. & Siohan, O. (2001). An auditory system-based feature for robust speech recognition. Proceedings Eurospeech. pp 619\u2013621."},{"key":"9236_CR22","doi-asserted-by":"crossref","unstructured":"Long, C. & Datta, S. (1996). Wavelet based feature extraction for phoneme recognition. 4th Int. Conf. Spok. Lang. Process. Philadelphia (USA), pp 264\u2013267.","DOI":"10.1109\/ICSLP.1996.607095"},{"key":"9236_CR23","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/34.192463","volume":"11","author":"S Mallat","year":"1989","unstructured":"Mallat, S. (1989). A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 674\u2013693.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9236_CR24","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s10772-011-9119-z","volume":"14","author":"ZB Messaoud","year":"2010","unstructured":"Messaoud, Z. B., & Hamida, A. B. (2010). Combining formant frequency based on variable order LPC coding with acoustic features for TIMIT phone recognition. International Journal of Speech Technology, Springer, 14, 393\u2013403.","journal-title":"International Journal of Speech Technology, Springer"},{"key":"9236_CR25","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/S0167-6393(02)00151-6","volume":"41","author":"P Niyogi","year":"2003","unstructured":"Niyogi, P., & Ramesh, P. (2003). The voicing feature for stop consonants: recognition experiments with continuously spoken alphabets. Speech Communication, 41, 349\u2013367.","journal-title":"Speech Communication"},{"key":"9236_CR26","volume-title":"An efficient auditory filterbank based on the Gammatone function","author":"RD Patterson","year":"1988","unstructured":"Patterson, R. D., Nimmo-Smith, I., Holdsworth, J., & Rice, P. (1988). An efficient auditory filterbank based on the Gammatone function. Cambridge: Appl. Psychol: Unit, Cambridge University."},{"key":"9236_CR27","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TASSP.1977.1162905","volume":"25","author":"LR Rabiner","year":"1977","unstructured":"Rabiner, L. R. (1977). On the use of autocorrelation analysis for pitch detection. IEEE Transactions on Acoustics Speech and Signal Processing, 25, 24\u201333.","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"9236_CR28","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition. Englewood Cliffs, USA: PTR Prentice-Hall."},{"key":"9236_CR29","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.csl.2008.03.004","volume":"24","author":"Y Shao","year":"2010","unstructured":"Shao, Y., Srinivasan, S., Jin, Z., & Wang, D. (2010). A computational auditory scene analysis system for speech segregation and robust speech recognition. Computer Speech & Language, Elsevier, 24, 77\u201393.","journal-title":"Computer Speech & Language, Elsevier"},{"key":"9236_CR30","doi-asserted-by":"crossref","unstructured":"Stark, A.P. & Paliwal, K.K. (2008). Speech analysis using instantaneous frequency deviation. the Interspeech. Brisbane, Australia, pp 2602\u20132605.","DOI":"10.21437\/Interspeech.2008-645"},{"key":"9236_CR31","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1016\/j.specom.2010.04.008","volume":"53","author":"H Yin","year":"2011","unstructured":"Yin, H., Hohmann, V., & Nadeu, C. (2011). Acoustic features for speech recognition based on Gammatone filterbank and instantaneous frequency. Speech Communication, 53, 707\u2013715.","journal-title":"Speech Communication"},{"key":"9236_CR32","unstructured":"Young, S.J., Evermann, G., Gales, M.J.F., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V. & Woodland, P.C. (2009). The HTK Book (for HTK Version 3.4). Construction 384."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9236-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-014-9236-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9236-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T22:17:04Z","timestamp":1689286624000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-014-9236-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,4]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["9236"],"URL":"https:\/\/doi.org\/10.1007\/s10772-014-9236-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,6,4]]}}}