{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T08:18:15Z","timestamp":1725524295570},"publisher-location":"Berlin, Heidelberg","reference-count":31,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540928911"},{"type":"electronic","value":"9783540928928"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-540-92892-8_8","type":"book-chapter","created":{"date-parts":[[2009,1,6]],"date-time":"2009-01-06T02:03:30Z","timestamp":1231207410000},"page":"63-73","source":"Crossref","is-referenced-by-count":1,"title":["Towards a New Image-Based Spectrogram Segmentation Speech Coder Optimised for Intelligibility"],"prefix":"10.1007","author":[{"given":"Keith A.","family":"Jellyman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas W. D.","family":"Evans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. M.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. S. D.","family":"Mason","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Martin, R.: Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors. In: Proc. IEEE ICASSP, vol.\u00a01, pp. 253\u2013256 (2002)","DOI":"10.1109\/ICASSP.2002.5743702"},{"key":"8_CR2","unstructured":"Beerends, J.G.: Extending p.862 PESQ for assessing speech intelligibility. White contribution COM 12-C2 to ITU-T Study, Group 12 (October 2004)"},{"issue":"9","key":"8_CR3","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/LSP.2003.815617","volume":"10","author":"N.R. Chong-White","year":"2003","unstructured":"Chong-White, N.R., Cox, R.V.: An intelligibility enhancement for the mixed excitation linear prediction speech coder. IEEE Signal Processing Letters\u00a010(9), 263\u2013266 (2003)","journal-title":"IEEE Signal Processing Letters"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Martin, R., Malah, D., Cox, R.V., Accardi, A.J.: A noise reduction preprocessor for mobile voice communication. EURASIP Journal on Applied Signal Processing, 1046\u20131058 (2004)","DOI":"10.1155\/S1110865704312138"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Demiroglu, C., Anderson, D.V.: A soft decision MMSE amplitude estimator as a noise preprocessor to speech coders using a glottal sensor. In: Proc. ICSLP, pp. 857\u2013860 (2004)","DOI":"10.21437\/Interspeech.2004-314"},{"issue":"2","key":"8_CR6","first-page":"533","volume":"14","author":"T.F. Quatieri","year":"2006","unstructured":"Quatieri, T.F., Brady, K., Messing, D., Campbell, J.P., Campbell, W.M., Brandstein, M.S., Clifford, C.J., Tardelli, J.D., Gatewood, P.D.: Exploiting nonacoustic sensors for speech encoding. IEEE Trans. on ASLP\u00a014(2), 533\u2013544 (2006)","journal-title":"IEEE Trans. on ASLP"},{"issue":"4","key":"8_CR7","first-page":"561","volume":"4","author":"Y. Hu","year":"2007","unstructured":"Hu, Y., Loizou, P.C.: A comparative intelligibility study of speech enhancement algorithms. ICASSP\u00a04(4), 561\u2013564 (2007)","journal-title":"ICASSP"},{"key":"8_CR8","unstructured":"Liu, W.M.: Objective assessment of comparative intelligibility. PhD Thesis, University of Wales Swansea University (2008)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Supplee, L.N., Cohn, R.P., Collura, J.S., McCree, A.V.: MELP: The new federal standard at 2400 bps. In: Proc. ICASSP, vol.\u00a02, pp. 1591\u20131594 (1997)","DOI":"10.1109\/ICASSP.1997.596257"},{"key":"8_CR10","doi-asserted-by":"publisher","first-page":"2915","DOI":"10.1109\/TSP.2002.805489","volume":"50","author":"C. Hory","year":"2002","unstructured":"Hory, C., Martin, N.: Spectrogram segmentation by means of statistical features for non-stationary signal interpretation. IEEE Trans. on Signal Processing\u00a050, 2915\u20132925 (2002)","journal-title":"IEEE Trans. on Signal Processing"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Cox, R.V.: Three new speech coders from the ITU cover a range of applications. IEEE Communications Magazine, 40\u201347 (1997)","DOI":"10.1109\/35.620524"},{"key":"8_CR12","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1109\/PROC.1980.11676","volume":"68","author":"J.D. Gibson","year":"1980","unstructured":"Gibson, J.D.: Adaptive prediction in speech differential encoding system. Proc. IEEE\u00a068, 488\u2013525 (1980)","journal-title":"Proc. IEEE"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Ekudden, E., Hagen, R., Johansson, I., Svedberg, J.: The adaptive multi-rate speech coder. In: Proc. IEEE Workshop on Speech Coding, pp. 117\u2013119 (1999)","DOI":"10.1109\/SCFT.1999.781503"},{"issue":"5","key":"8_CR14","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1109\/49.138988","volume":"10","author":"J.-H. Chen","year":"1992","unstructured":"Chen, J.-H., Cox, R.V., Lin, Y.-C., Jayant, N., Melchner, M.J.: A low-delay CELP coder for the CCITT 16 kb\/s speech coding standard. IEEE Selected Areas in Communications\u00a010(5), 830\u2013849 (1992)","journal-title":"IEEE Selected Areas in Communications"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Vary, P., Hellwig, K., Hofmann, R., Sluyter, R.J., Galand, C., Rosso, M.: Speech codec for the european mobile radio system. In: Proc. ICASSP, pp. 227\u2013230 (1988)","DOI":"10.1109\/ICASSP.1988.196556"},{"key":"8_CR16","unstructured":"Tremain, T.E.: The government standard linear predictive coding algorithm: LPC-10. In: Speech Technology, pp. 40\u201349 (1982)"},{"key":"8_CR17","unstructured":"Sun Microsystems. CCITT ADPCM encoder G.711, G.721, G.723, encode (14\/04\/2008), ftp:\/\/ftp.cwi.nl\/pub\/audio\/ccitt-adpcm.tar.gz"},{"key":"8_CR18","unstructured":"3GPP. European digital cellular telecommunication system 4750.. 12200 bits\/s speech CODEC for adaptive multi-rate speech traffic channels, encoder, v6.0.0 (29\/06\/2008), http:\/\/www.3gpp.org\/ftp\/Specs\/html-info\/26073.htm"},{"key":"8_CR19","unstructured":"Zatsman, A., Concannon, M.: 16 kb\/s low-delay CELP algorithm, ccelp, v2.0 (14\/04\/2008), ftp:\/\/svr-ftp.eng.cam.ac.uk\/comp.speech\/coding\/ldcelp-2.0.tar.gz"},{"key":"8_CR20","unstructured":"Jutta. ETSI 06.10 GSM-FR, toast, v1.8 (14\/04\/2008), http:\/\/kbs.cs.tu-berlin.de\/~jutta\/toast.html"},{"key":"8_CR21","unstructured":"Texas Instruments, Inc. 2.4 kb\/s proposed federal standard MELP speech coder, melp, v1.2 (14\/04\/2008)"},{"key":"8_CR22","unstructured":"Fingerhut, A.: U.S. department of defence LPC-10 2400bps voice coder, nuke, v1.5 (14\/04\/2008), http:\/\/www.arl.wustl.edu\/~jaf\/lpc\/"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W.M., Jellyman, K.A., Mason, J.S., Evans, N.W.D.: Assessment of objective quality measures for speech intelligibility estimation. In: Proc. ICASSP (2006)","DOI":"10.1109\/ICASSP.2006.1660248"},{"key":"8_CR24","unstructured":"ITU recommendation P.56. Objective measurement of active speech level. ITU (1993)"},{"key":"8_CR25","unstructured":"Hirsch, H.G., Pearce, D.: The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. ISCA ITRW ASR2000 Automatic Speech Recognition: Challenges for the next Millenium (2000)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W.M., Jellyman, K.A., Evans, N.W.D., Mason, J.S.D.: Assessment of objective quality measures for speech intelligibility. Publication in ICSLP (accepted, 2008)","DOI":"10.21437\/Interspeech.2008-220"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Romero Rodriguez, F., Liu, W.M., Evans, N.W.D., Mason, J.S.D.: Morphological filtering of speech spectrograms in the context of additive noise. In: Proc. Eurospeech (2003)","DOI":"10.21437\/Eurospeech.2003-46"},{"key":"8_CR28","unstructured":"Evans, N.W.D.: Spectral subtraction for speech enhancement and automatic speech recognition. PhD Thesis, University of Wales Swansea (2003)"},{"issue":"4","key":"8_CR29","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1109\/TASSP.1986.1164910","volume":"34","author":"R.J. McAulay","year":"1986","unstructured":"McAulay, R.J., Quatieri, T.F.: Speech analysis\/synthesis based on a sinusoidal representation. IEEE Trans. ASSP\u00a034(4), 744\u2013754 (1986)","journal-title":"IEEE Trans. ASSP"},{"key":"8_CR30","unstructured":"ImageMagick\u00a0Studio LLC. Imagemagick, v6.3.0, http:\/\/www.imagemagick.org"},{"key":"8_CR31","unstructured":"Kuhn, M.: JBIG-KIT package, v1.6, http:\/\/www.cl.cam.ac.uk\/~mgk25\/jbigkit\/"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-92892-8_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T11:07:21Z","timestamp":1684840041000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-92892-8_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783540928911","9783540928928"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-92892-8_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}