On smoothing articulatory trajectories obtained from Gaussian mixture model based acoustic-to-articulatory inversion

被引：6

作者：

Ghosh, Prasanta K. ^{[1
]}

Narayanan, Shrikanth S. ^{[2
]}

机构：

[1] Indian Inst Sci IISc, Bangalore 560012, Karnataka, India

[2] Univ So Calif, Dept Elect Engn, Los Angeles, CA 90089 USA

来源：

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA | 2013年 / 134卷 / 02期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1121/1.4813590

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

It is well-known that the performance of acoustic-to-articulatory inversion improves by smoothing the articulatory trajectories estimated using Gaussian mixture model (GMM) mapping (denoted by GMM+Smoothing). GMM+Smoothing also provides similar performance with GMM mapping using dynamic features, which integrates smoothing directly in the mapping criterion. Due to the separation between smoothing and mapping, what objective criterion GMM+Smoothing optimizes remains unclear. In this work a new integrated smoothness criterion, the smoothed-GMM (SGMM), is proposed. GMM+Smoothing is shown, both analytically and experimentally, to be identical to the asymptotic solution of SGMM suggesting GMM+Smoothing to be a near optimal solution of SGMM. (C) 2013 Acoustical Society of America

引用

页码：EL258 / EL264

页数：7

共 50 条

[1] A SPARSE SMOOTHING APPROACH FOR GAUSSIAN MIXTURE MODEL BASED ACOUSTIC-TO-ARTICULATORY INVERSION
Sudhakar, Prasad
Jacques, Laurent
Ghosh, Prasanta Kumar
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[2] Sparse smoothing of articulatory features from Gaussian mixture model based acoustic-to-articulatory inversion: Benefit to speech recognition
Sudhakar, Prasad
Ghosh, Prasanta Kumar
[J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 169 - 173
[3] Acoustic-to-Articulatory Inversion Mapping based on Latent Trajectory Gaussian Mixture Model
Tobing, Patrick Lumban
Toda, Tomoki
Kameoka, Hirokazu
Nakamura, Satoshi
[J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 953 - 957
[4] Formant Trajectories for Acoustic-to-Articulatory Inversion
Ozbek, I. Yuecel
Hasegawa-Johnson, Mark
Demirekler, Muebeccel
[J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2783 - +
[5] Acoustic-to-Articulatory Inversion based on Local Regression
Al Moubayed, Samer
Ananthakrishnan, G.
[J]. 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 937 - 940
[6] Jerk Minimization for Acoustic-To-Articulatory Inversion
Rajpal, Avni
Patil, Hemant A.
[J]. 9th ISCA Speech Synthesis Workshop, SSW 2016, 2016, : 82 - 87
[7] Acoustic-to-Articulatory Inversion with Deep Autoregressive Articulatory-WaveNet
Bozorg, Narjes
Johnson, Michael T.
[J]. INTERSPEECH 2020, 2020, : 3725 - 3729
[8] Acoustic-to-articulatory inversion from infants' vowel vocalizations
Oohashi, Hiroki
Watanabe, Hama
Taga, Gentaro
[J]. NEUROSCIENCE RESEARCH, 2011, 71 : E286 - E286
[9] Incorporation of phonetic constraints in acoustic-to-articulatory inversion
Potard, Blaise
Laprie, Yves
Ouni, Slim
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2008, 123 (04): : 2310 - 2323
[10] Modeling the articulatory space using a hypercube codebook for acoustic-to-articulatory inversion
Ouni, S
Laprie, Y
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2005, 118 (01): : 444 - 460

← 1 2 3 4 5 →