PMID- 29960421
OWN - NLM
STAT- MEDLINE
DCOM- 20191029
LR  - 20191029
IS  - 1520-8524 (Electronic)
IS  - 0001-4966 (Linking)
VI  - 143
IP  - 6
DP  - 2018 Jun
TI  - Reconstruction of articulatory movements during neutral speech from those during 
      whispered speech.
PG  - 3352
LID - 10.1121/1.5039750 [doi]
AB  - A transformation function (TF) that reconstructs neutral speech articulatory 
      trajectories (NATs) from whispered speech articulatory trajectories (WATs) is 
      investigated, such that the dynamic time warped (DTW) distance between the 
      transformed whispered and the original neutral articulatory movements is 
      minimized. Three candidate TFs are considered: an affine function with a diagonal 
      matrix ( A(d)) which reconstructs one NAT from the corresponding WAT, an affine 
      function with a full matrix ( A(f)) and a deep neural network (DNN) based 
      nonlinear function which reconstruct each NAT from all WATs. Experiments reveal 
      that the transformation could be approximated well by A(f), since it generalizes 
      better across subjects and achieves the least DTW distance of 5.20 (+/-1.27) mm (on 
      average), with an improvement of 7.47%, 4.76%, and 7.64% (relative) compared to 
      that with A(d), DNN, and the best baseline scheme, respectively. Further analysis 
      to understand the differences in neutral and whispered articulation reveals that 
      the whispered articulators exhibit exaggerated movements in order to reconstruct 
      the lip movements during neutral speech. It is also observed that among the 
      articulators considered in the study, the tongue exhibits a higher precision and 
      stability while whispering, implying that subjects control their tongue movements 
      carefully in order to render an intelligible whispered speech.
FAU - G, Nisha Meenakshi
AU  - G NM
AD  - Electrical Engineering, Indian Institute of Science, Bangalore-560012, India.
FAU - Ghosh, Prasanta Kumar
AU  - Ghosh PK
AD  - Electrical Engineering, Indian Institute of Science, Bangalore-560012, India.
LA  - eng
PT  - Comparative Study
PT  - Journal Article
PL  - United States
TA  - J Acoust Soc Am
JT  - The Journal of the Acoustical Society of America
JID - 7503051
SB  - IM
MH  - Biomechanical Phenomena
MH  - Deep Learning
MH  - Electromagnetic Phenomena
MH  - Female
MH  - Humans
MH  - Lip/anatomy & histology/*physiology
MH  - Male
MH  - *Models, Theoretical
MH  - Nonlinear Dynamics
MH  - *Phonetics
MH  - *Speech Acoustics
MH  - Speech Intelligibility
MH  - Time Factors
MH  - Tongue/anatomy & histology/*physiology
MH  - *Voice Quality
EDAT- 2018/07/02 06:00
MHDA- 2019/10/30 06:00
CRDT- 2018/07/02 06:00
PHST- 2018/07/02 06:00 [entrez]
PHST- 2018/07/02 06:00 [pubmed]
PHST- 2019/10/30 06:00 [medline]
AID - 10.1121/1.5039750 [doi]
PST - ppublish
SO  - J Acoust Soc Am. 2018 Jun;143(6):3352. doi: 10.1121/1.5039750.