{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:34:52Z","timestamp":1790620492156,"version":"4.1.0"},"reference-count":39,"publisher":"Acoustical Society of America (ASA)","issue":"4","content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,10,1]]},"abstract":"<jats:p>The many-to-one mapping from representations in the speech articulatory space to acoustic space renders the associated acoustic-to-articulatory inverse mapping non-unique. Among various techniques, imposing smoothness constraints on the articulator trajectories is one of the common approaches to handle the non-uniqueness in the acoustic-to-articulatory inversion problem. This is because, articulators typically move smoothly during speech production. A standard smoothness constraint is to minimize the energy of the difference of the articulatory position sequence so that the articulator trajectory is smooth and low-pass in nature. Such a fixed definition of smoothness is not always realistic or adequate for all articulators because different articulators have different degrees of smoothness. In this paper, an optimization formulation is proposed for the inversion problem, which includes a generalized smoothness criterion. Under such generalized smoothness settings, the smoothness parameter can be chosen depending on the specific articulator in a data-driven fashion. In addition, this formulation allows estimation of articulatory positions recursively over time without any loss in performance. Experiments with the MOCHA TIMIT database show that the estimated articulator trajectories obtained using such a generalized smoothness criterion have lower RMS error and higher correlation with the actual measured trajectories compared to those obtained using a fixed smoothness constraint.<\/jats:p>","DOI":"10.1121\/1.3455847","type":"journal-article","created":{"date-parts":[[2010,10,19]],"date-time":"2010-10-19T13:15:29Z","timestamp":1287494129000},"page":"2162-2172","update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":51,"title":["A generalized smoothness criterion for acoustic-to-articulatory inversion"],"prefix":"10.1121","volume":"128","author":[{"given":"Prasanta Kumar","family":"Ghosh","sequence":"first","affiliation":[{"name":"University of Southern California Department of Electrical Engineering, Signal Analysis and Interpretation Laboratory, , Los Angeles, California 90089"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California Department of Electrical Engineering, Signal Analysis and Interpretation Laboratory, , Los Angeles, California 90089"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"231","published-online":{"date-parts":[[2010,10,18]]},"reference":[{"key":"2023072022172848900_c1","first-page":"152","article-title":"Un modele articulatoire de la langue avec des composantes lineaires (An articulatory model of the tongue with linear components)","year":"1979"},{"key":"2023072022172848900_c2","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/978-94-009-2037-8","article-title":"Compensatory articulation during speech: Evidence from the analysis and synthesis of vocal tract shapes using an articulatory model","volume-title":"Speech Production and Speech Modelling","author":"Hardcastle","year":"1990"},{"key":"2023072022172848900_c3","first-page":"1","article-title":"Speech synthesis","year":"1962"},{"key":"2023072022172848900_c4","first-page":"219","article-title":"Towards an articulatory phonology","volume-title":"Phonology Yearbook 2","author":"Ewen","year":"1986"},{"key":"2023072022172848900_c5","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1017\/S0952675700001019","article-title":"Articulatory gestures as phonological units","volume":"6","year":"1989","journal-title":"Phonology"},{"key":"2023072022172848900_c6","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S0095-4470(19)30376-6","article-title":"Gestural specification using dynamically-defined articulatory structures","volume":"18","year":"1990","journal-title":"J. Phonetics"},{"key":"2023072022172848900_c7","first-page":"305","article-title":"A multichannel articulatory database and its application for automatic speech recognition","year":"2000"},{"key":"2023072022172848900_c8","doi-asserted-by":"publisher","first-page":"3246","DOI":"10.1121\/1.411699","article-title":"Adding articulatory features to acoustic features for automatic speech recognition","volume":"97","year":"1995","journal-title":"J. Acoust. Soc. Am."},{"key":"2023072022172848900_c9","first-page":"145","article-title":"Continuous speech recognition using articulatory data","year":"2000"},{"key":"2023072022172848900_c10","first-page":"254","article-title":"An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces","year":"2000"},{"key":"2023072022172848900_c11","unstructured":"K.\u2008Kirchhoff, \u201cRobust speech recognition using articulatory information,\u201d Ph.D. thesis, University of Bielefeld, Bielefeld, Germany (1999)."},{"key":"2023072022172848900_c12","first-page":"1489","article-title":"The entropy of the articulatory phonological code: Recognizing gestures from tract variables","year":"2008"},{"key":"2023072022172848900_c13","article-title":"An empirical investigation of the nonuniqueness in the acoustic-to-articulatory mapping","year":"2007"},{"key":"2023072022172848900_c14","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1121\/1.381848","article-title":"Inversion of articulatory-to-acoustic transformation in the vocal tract by a computer-sorting technique","volume":"63","year":"1978","journal-title":"J. Acoust. Soc. Am."},{"key":"2023072022172848900_c15","article-title":"Acoustic-to-articulatory inversion of speech: A review","year":"2003"},{"key":"2023072022172848900_c16","volume-title":"Regularization Methods for Ill-Posed Problem","year":"1993"},{"key":"2023072022172848900_c17","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/S0167-6393(99)00031-X","article-title":"Estimation of stability and accuracy of inverse problem solution for the vocal tract","volume":"30","year":"2000","journal-title":"Speech Commun."},{"key":"2023072022172848900_c18","first-page":"588","article-title":"Dynamic programming search of articulatory code-books","year":"1989"},{"key":"2023072022172848900_c19","first-page":"485","article-title":"Acoustic-to-articulatory parameter mapping using an assembly of neural networks","year":"1991"},{"key":"2023072022172848900_c20","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1121\/1.416001","article-title":"Accurate recovery of articulator positions from acoustics: New conclusions based on human data","volume":"100","year":"1996","journal-title":"J. Acoust. Soc. Am."},{"key":"2023072022172848900_c21","first-page":"1129","article-title":"Acoustic-to-articulatory inversion mapping with Gaussian mixture model","year":"2004"},{"key":"2023072022172848900_c22","first-page":"577","article-title":"A trajectory mixture density network for the acoustic-articulatory inversion mapping","year":"2006"},{"key":"2023072022172848900_c23","first-page":"279","article-title":"Estimation of articulatory motion","volume-title":"Dynamic Aspects of Speech Production","year":"1976"},{"key":"2023072022172848900_c24","first-page":"477","article-title":"Estimation of articulatory trajectory by Kalman filter","volume-title":"Signal Processing III: Theories and Application","author":"Young","year":"1986"},{"key":"2023072022172848900_c25","first-page":"1401","article-title":"Maximum-likelihood estimation for articulatory speech recognition using a stochastic target mode","year":"1995"},{"key":"2023072022172848900_c26","first-page":"237","article-title":"Acoustic-to-articulatory inversion using dynamic and phonological constraint","year":"2000"},{"key":"2023072022172848900_c27","unstructured":"K.\u2008Richmond, \u201cEstimating articulatory parameters from the acoustic speech signal,\u201d Ph.D. thesis, Edinburgh University, Edinburgh (2002)."},{"key":"2023072022172848900_c28","article-title":"Mixture density networks, human articulatory data and acoustic-to-articulatory inversion of continuous speech","year":"2001"},{"key":"2023072022172848900_c29","first-page":"429","article-title":"Voice mimic system using an articulatory codebook for estimation of vocal tract shape","year":"1997"},{"key":"2023072022172848900_c30","first-page":"1101","article-title":"Determining vocal tract shape by applying dynamic constraints","year":"1985"},{"key":"2023072022172848900_c31","first-page":"1233","article-title":"Deriving articulatory representations from speech with various excitation modes","year":"1996"},{"key":"2023072022172848900_c32","article-title":"Data-driven articulatory inversion incorporating articulator priors","year":"2008"},{"key":"2023072022172848900_c33","doi-asserted-by":"publisher","first-page":"S33","DOI":"10.1121\/1.2019340","article-title":"Perioral biomechanics and its relation to labial motor control","volume":"71","year":"1982","journal-title":"J. Acoust. Soc. Am."},{"key":"2023072022172848900_c34","volume-title":"Statistical and Adaptive Signal Processing: Spectral Estimation, Signal Modeling, Adaptive Filtering and Array Processing","year":"2005"},{"key":"2023072022172848900_c35","volume-title":"Pattern Classification and Scene Analysis","year":"1983"},{"key":"2023072022172848900_c36","doi-asserted-by":"publisher","volume-title":"Elements of Information Theory","year":"1991","DOI":"10.1002\/0471200611"},{"key":"2023072022172848900_c37","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/18.761290","article-title":"Estimation of the information by an adaptive partition of the observation space","volume":"45","year":"1999","journal-title":"IEEE Trans. Inf. Theory"},{"key":"2023072022172848900_c38","first-page":"2469","article-title":"A comparison of acoustic features for articulatory inversion","year":"2007"},{"key":"2023072022172848900_c39","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.specom.2007.09.001","article-title":"Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model","volume":"50","year":"2008","journal-title":"Speech Commun."}],"container-title":["The Journal of the Acoustical Society of America"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/128\/4\/2162\/13784101\/2162_1_online.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/128\/4\/2162\/13784101\/2162_1_online.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T22:21:46Z","timestamp":1689891706000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jasa\/article\/128\/4\/2162\/683360\/A-generalized-smoothness-criterion-for-acoustic-to"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,1]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2010,10,1]]}},"URL":"https:\/\/doi.org\/10.1121\/1.3455847","relation":{},"ISSN":["0001-4966","1520-8524"],"issn-type":[{"value":"0001-4966","type":"print"},{"value":"1520-8524","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2010,10]]},"published":{"date-parts":[[2010,10,1]]}}}