Discrimination of Sonorants from Fricatives Using a Scalar Feature Derived from Linear Prediction Coefficients

Ananthapadmanabha, TV and Ramakrishnan, AG and Madhavaraj, A and Balachandran, P (2020) Discrimination of Sonorants from Fricatives Using a Scalar Feature Derived from Linear Prediction Coefficients. In: INDICON 2018 - 15th IEEE India Council International Conference, 16-18 Dec. 2018, Coimbatore, India, India.

PDF IND_2018_15TH_IND_COU_INT_CON_8986997.pdf - Published Version Restricted to Registered users only Download (467kB) | Request a copy

Abstract

The sum of linear prediction coefficients (LPCs) is proposed as an effective feature in discriminating between sonorants and fricatives in continuous speech. On the closed set of sonorant and fricative frames of the entire TIMIT test database, a classification accuracy of 98.23 is obtained. When this feature is combined with three other features derived from the LPCs, the feature vector achieves an accuracy of 98.27 using a linear support vector machine classifier. The accuracy increases to 98.41 with mel frequency cepstral coefficients also added. The robustness of the feature has been tested on additive white, babble and pink noise. © 2018 IEEE.

Item Type:	Conference Paper
Publication:	INDICON 2018 - 15th IEEE India Council International Conference
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	cited By 0; Conference of 15th IEEE India Council International Conference, INDICON 2018 ; Conference Date: 16 December 2018 Through 18 December 2018; Conference Code:158392
Keywords:	Forecasting; Image segmentation; Support vector machines, fricative; Linear prediction; manner class; Phonetic features; sonorant, Classification (of information)
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	21 Sep 2020 11:07
Last Modified:	21 Sep 2020 11:07
URI:	http://eprints.iisc.ac.in/id/eprint/65146

Actions (login required)

View Item