Estimation of stability and accuracy of inverse problem solution for the vocal tract

Сорокин, В. Н.; Леонов, А. С.; Trushkin, A.

doi:10.1016/s0167-6393(99)00031-x

Cited by 22 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[17][18][19][20][21] Sorokin et al 17 chose a regularizing term that prevents inverse solutions from deviating too much from the neutral position of articulators. Schroeter and Sondhi 18 presented a method based on dynamic programming ͑DP͒ to search articulatory codebooks with a penalty factor for large "articulatory efforts," that is, fast changes in the vocal tract so that the estimated articulator trajectories are smoothly evolving.…”

Section: Introductionmentioning

confidence: 99%

A generalized smoothness criterion for acoustic-to-articulatory inversion

Ghosh

Narayanan

2010

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

A generalized smoothness criterion for acoustic-to-articulatory inversion

Ghosh

Narayanan

2010

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…categories: analysis-by-synthesis approaches and datadriven approaches. Several articulatory inversion methods are based on the analysis-by-synthesis approach, which is a closed-loop optimization procedure that involves the comparison of the spectrum of synthesized speech to the measured speech at consecutive frames, for example [4][5][6][7][8].…”

Section: Databasementioning

confidence: 99%

“…(6), can also be expressed as a GMM as follows, (6) where the parameter in Eq. (6) corresponding to conditional mean is calculated by Eq.…”

Section: Acoustic-to-articulatory Mapping Approachmentioning

confidence: 99%

Subject-independent acoustic-to-articulatory mapping of fricative sounds by using vocal tract length normalization

Sepúlveda-Sepúlveda

Castellanos-Domínguez

Gómez-Vilda

2015

Rev. Fac. Ing. Antioquia

View full text Add to dashboard Cite

“…In the first place, a full three level WPT decomposition is performed, which splits the frequency components within the range [0, 8] kHz into eight bands; where each is of 1 kHz bandwidth approximately. Then, energy localized in the bands [4,5] kHz, [5,6] kHz, [6,7] kHz, and [7,8] Likewise, to accomplish the time plane partition, the acoustic speech signal is parameterized using 20 ms frames and ∆t = 10 ms steps, so a rate frame of 100 Hz is performed [16]. Acoustic information within time interval ranging from t − t a = t − 200 ms to t + t b = t + 300 ms is parameterized.…”

Section: Acoustic Representation Based On Wavelet Packet Transformmentioning

confidence: 99%

“…The question of how the articulatory information, which come from Electro-Magnetic Articulograph (EMA) systems in present work, is coded in the speech signal remains of practical and theoretical relevance. In particular, the knowledge of the distribution of the articulatory influence on the acoustic speech signal is useful in those applications involving articulatory inversion tasks, whose main goal is to infer the articulators position based on the information immersed in the acoustic speech signal [7], [8].…”

Section: Introductionmentioning

confidence: 99%

Time-Frequency Energy Features for Articulator Position Inference on Stop Consonants

Sepúlveda-Sepúlveda

Castellanos-Domínguez

2012

ing.cienc.

View full text Add to dashboard Cite

Acoustic-to-Articulatory inversion offers new perspectives and interesting applications in the speech processing field; however, it remains an open issue. This paper presents a method to estimate the distribution of the articulatory information contained in the stop consonants' acoustics, whose parametrization is achieved by using the wavelet packet transform. The main focus is on measuring the relevant acoustic information, in terms of statistical association, for the inference of the position of critical articulators involved in stop consonants production. The rank correlation Kendall coefficient is used as the relevance measure. The maps of relevant time-frequency features are calculated for the MOCHA-TIMIT database; from which, stop consonants are extracted and analysed. The proposed method obtains a set of time-frequency components closely related to articulatory phenemenon, which offers a deeper understanding into the relationship between the articulatory and acoustical phenomena. The relevant maps are tested into an acoustic-to-articulatory mapping system based on Gaussian mixture models, where it is shown they are suitable for improving the performance of such a systems over stop consonants. The method 1 Magíster en Automatización, PhD(c) en Ingeniería-Automática, Universidad Nacional, Manizales, Colombia, alexander.sepulveda.sepulveda@gmail.com. 37|Time-Frequency Energy Features for Articulator Position Inference on Stop Consonants could be extended to other manner of articulation categories, e.g. fricatives, in order to adapt present method to acoustic-to-articulatory mapping systems over whole speech.Key words: acoustic-to-Articulatory inversion, Gaussian mixture models, articulatory phonetics, time-frequency features.Características de tiempo-frecuencia para la estimación de la posición de los órganos articuladores en consonantes explosivas Resumen La inversión articulatoria ofrece nuevas perspectivas y aplicaciones interesantes en el campo de la voz; sin embargo, es aún un problema por resolver. El presente trabajo ofrece un método para la estimación de la distribución de la información articulatoria contenida en la acústica de consonantes explosivas, cuya parametrización se realiza mediante la transformada wavelet packet. El trabajo se centra principalmente en estimar la información acústica relevante, en términos de asociación estadística, para la inferencia de la posición de los órganos articuladores críticos involucrados en la producción de consonantes explosivas. Se usa el coeficiente de Kendall a modo de medida de relevancia. Los mapas de relevancia de tiempo-frecuencia se calculan para la base de datos MOCHA-TIMIT; de la cual, las zonas correspondientes a las consonantes explosivas son analizados. El método propuesto entrega un conjunto de componentes de tiempo-frecuencia intimamente relacionados al fenómeno articulatorio, lo cual ofrece un entendimiento más profundo de la relación existente entre los fenómenos articulatorio y acústico. Los mapas de relevancia se prueban en un sistem...

show abstract

Estimation of stability and accuracy of inverse problem solution for the vocal tract

Cited by 22 publications

References 55 publications

A generalized smoothness criterion for acoustic-to-articulatory inversion

A generalized smoothness criterion for acoustic-to-articulatory inversion

Subject-independent acoustic-to-articulatory mapping of fricative sounds by using vocal tract length normalization

Time-Frequency Energy Features for Articulator Position Inference on Stop Consonants

Contact Info

Product

Resources

About