Method and Apparatus for Recognizing Human Emotion Expressions based on Speech Signal

Paidi Gangamohan; Pratibha Moogi; Sudarsana Kadiri; Vinay Kumar Mittal; Bayya Yegnanarayana

Method and Apparatus for Recognizing Human Emotion Expressions based on Speech Signal

Paidi Gangamohan (Inventor)
, Pratibha Moogi (Inventor)
, Sudarsana Kadiri (Inventor)
, Vinay Kumar Mittal (Inventor)
, Bayya Yegnanarayana (Inventor)

Not published at Aalto University

Samsung R&D India
International Institute of Information Technology Hyderabad

Research output: Patent

Abstract

A method and apparatus for recognizing human emotion expressions based on speech signal is disclosed. In one embodiment, a method includes filtering an input speech signal corresponding to a voiced acoustic expression of an individual and determining glottal closure instance (GCI) locations in the speech signal using the filtered signal. Further, the method includes computing instantaneous values of a set of acoustic features of the speech signal using the estimated GCI locations in the speech signal. The instantaneous values of the set of acoustic features are normalized with reference to a same set of acoustic features of a neutral speech signal associated with the individual. A multi–dimensional joint distribution is generated based on the normalized instantaneous values of acoustic features and matched with a pre-defined emotion specific template. The Moreover, the method includes determining a human emotion expression associated with the individual by calculating the number of matched found.

Original language	English
Patent number	IN4854CH2013
IPC	G10L15/00
Priority date	28/10/2013
Filing date	28/10/2013
Publication status	Published - 8 May 2015
MoE publication type	H1 Granted patent

Cite this

@misc{b3ec474d88e849b3b88c8812b855adfe,

title = "Method and Apparatus for Recognizing Human Emotion Expressions based on Speech Signal",

abstract = "A method and apparatus for recognizing human emotion expressions based on speech signal is disclosed. In one embodiment, a method includes filtering an input speech signal corresponding to a voiced acoustic expression of an individual and determining glottal closure instance (GCI) locations in the speech signal using the filtered signal. Further, the method includes computing instantaneous values of a set of acoustic features of the speech signal using the estimated GCI locations in the speech signal. The instantaneous values of the set of acoustic features are normalized with reference to a same set of acoustic features of a neutral speech signal associated with the individual. A multi{\textendash}dimensional joint distribution is generated based on the normalized instantaneous values of acoustic features and matched with a pre-defined emotion specific template. The Moreover, the method includes determining a human emotion expression associated with the individual by calculating the number of matched found.",

author = "Paidi Gangamohan and Pratibha Moogi and Sudarsana Kadiri and Mittal, \{Vinay Kumar\} and Bayya Yegnanarayana",

year = "2015",

month = may,

day = "8",

language = "English",

type = "Patent",

note = "IN4854CH2013; G10L15/00",

}

TY - PAT

T1 - Method and Apparatus for Recognizing Human Emotion Expressions based on Speech Signal

AU - Gangamohan, Paidi

AU - Moogi, Pratibha

AU - Kadiri, Sudarsana

AU - Mittal, Vinay Kumar

AU - Yegnanarayana, Bayya

PY - 2015/5/8

Y1 - 2015/5/8

N2 - A method and apparatus for recognizing human emotion expressions based on speech signal is disclosed. In one embodiment, a method includes filtering an input speech signal corresponding to a voiced acoustic expression of an individual and determining glottal closure instance (GCI) locations in the speech signal using the filtered signal. Further, the method includes computing instantaneous values of a set of acoustic features of the speech signal using the estimated GCI locations in the speech signal. The instantaneous values of the set of acoustic features are normalized with reference to a same set of acoustic features of a neutral speech signal associated with the individual. A multi–dimensional joint distribution is generated based on the normalized instantaneous values of acoustic features and matched with a pre-defined emotion specific template. The Moreover, the method includes determining a human emotion expression associated with the individual by calculating the number of matched found.

AB - A method and apparatus for recognizing human emotion expressions based on speech signal is disclosed. In one embodiment, a method includes filtering an input speech signal corresponding to a voiced acoustic expression of an individual and determining glottal closure instance (GCI) locations in the speech signal using the filtered signal. Further, the method includes computing instantaneous values of a set of acoustic features of the speech signal using the estimated GCI locations in the speech signal. The instantaneous values of the set of acoustic features are normalized with reference to a same set of acoustic features of a neutral speech signal associated with the individual. A multi–dimensional joint distribution is generated based on the normalized instantaneous values of acoustic features and matched with a pre-defined emotion specific template. The Moreover, the method includes determining a human emotion expression associated with the individual by calculating the number of matched found.

UR - https://worldwide.espacenet.com/publicationDetails/biblio?CC=IN&NR=4854CH2013A&KC=A&FT=D

UR - https://www.patentguru.com/IN4854CH2013A

M3 - Patent

M1 - IN4854CH2013

Y2 - 2013/10/28

ER -

Method and Apparatus for Recognizing Human Emotion Expressions based on Speech Signal

Abstract

Other files and links

Fingerprint

Cite this