ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Low resource acoustic-to-articulatory inversion using bi-directional long short term memory

Illa, Aravind and Ghosh, Prasanta Kumar (2018) Low resource acoustic-to-articulatory inversion using bi-directional long short term memory. In: 19th Annual Conference of the International Speech Communication, 2 September 2018 to 6 September, Hyderabad International Convention Centre (HICC)Hyderabad, pp. 3122-3126.

[img] PDF
Interspeech (10)2018.pdf - Published Version
Restricted to Registered users only

Download (313kB) | Request a copy
Official URL: https://dx.doi.org/10.21437/Interspeech.2018-1843


Estimating articulatory movements from speech acoustic features is known as acoustic-to-articulatory inversion (AAI). Large amount of parallel data from speech and articulatory motion is required for training an AAI model in a subject dependent manner, referred to as subject dependent AAI (SD-AM). Electromagnetic articulograph (EMA) is a promising technology to record such parallel data, but it is expensive, time consuming and tiring for a subject. In order to reduce the demand for parallel acoustic-articulatory data in the AAI task for a subject, we, in this work, propose a subject-adaptative AAI method (SA-AAI) from an existing AAI model which is trained using large amount of parallel data from a fixed set of subjects. Experiments are performed with 30 subjects' acoustic-articulatory data and AM is trained using BLSTM network to examine the amount of data needed from a new target subject for the SAAAI to achieve an AAI performance equivalent to that of SDAAI. Experimental results reveal that the proposed SA-AAI performs similar to that of the SD-AAI with-.62.5% less training data. Among different articulators, the SA-AAI performance for tongue articulators matches with the corresponding SD-AAI performance with only,-,12.5% of the data used for SD-AAI training.

Item Type: Conference Proceedings
Series.: Interspeech
Additional Information: 19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018), Hyderabad, INDIA, AUG 02-SEP 06, 2018
Keywords: acoustic-to-articulatory inversion; BLSTM network; Adaptation
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 09 Jun 2020 06:03
Last Modified: 09 Jun 2020 06:03
URI: http://eprints.iisc.ac.in/id/eprint/62931

Actions (login required)

View Item View Item