System for indicating emotional attitudes through intonation analysis and methods thereof
AssigneeExaudios Technologies
InventorsYoram Levanon, Lan Lossos
Life of this patent
Estimating the term…
Abstract
The present invention discloses means and method for indicating emotional attitudes of a speaker, either human or animal, according to voice intonation. The invention also discloses a method for advertising, marketing, educating, or lie detecting by indicating emotional attitudes of a speaker and a method of providing remote service by a group comprising at least one observer to at least one speaker. The invention also discloses a system for indicating emotional attitudes of a speaker comprising a glossary of intonations relating intonations to emotions attitudes.
Claims14
A method for indicating emotional attitudes of a speaker according to voice tone, said method comprising:
- a. obtaining a database comprising reference tones and reference emotional attitudes corresponding to each of said reference tones;
- b. pronouncing at least one word by a speaker for the duration of a sample period;
- c. recording said at least one word so as to obtain a signal representing sound volume as a function of frequency for said sample period;
- d. processing said signal so as to obtain voice characteristics of said speaker, wherein said processing includes determining a Function A, said Function A being defined as the average or maximum sound volume as a function of sound frequency, from within a range of frequencies measured in said sampled period, and wherein said processing further includes determining a Function B, said Function B defined as the averaging, or maximizing of said function A over said range of frequencies and dyadic multiples thereof;
- e. comparing said voice characteristics to said reference tones so as to indicate at least one of said reference emotional attitudes.
A method for indicating emotional attitudes of an animal, said method comprising:
- a. defining a set of sounds that an animal produces;
- b. obtaining a database comprising reference tones and reference emotional attitudes for each sound of said set of sounds for each of said reference tones;
- c. producing, by said animal, at least one sound of said set of sounds;
- d. recording said at least one sound produced by said animal for the duration of a sample period so as to obtain a signal representing sound volume as a function of frequency for said sample period;
- e. processing said signal so as to obtain sound characteristics, wherein said processing includes determining a Function A, said Function A being defined as the average or maximum sound volume as a function of sound frequency, from within a range of frequencies measured in said sample period, and wherein said processing further includes determining a Function B, said Function B defined as the averaging, or maximizing, of said function A over said range of frequencies and dyadic multiples thereof
- f. comparing said sound characteristics to said reference tones so as to indicate at least one reference emotional attitude.
A system for indicating at least one emotional attitude of a speaker using voice tone analysis, said system comprising:
- a. a sound recorder adapted to record a word or set of words that is repeatedly pronounced by a speaker for the duration of a sample period, and to produce a signal representing sound volume as a function of frequency for said sample period,
- b. processing means coupled to said recorder, for processing said signal so as to obtain voice characteristics relating to the tone of said speaker, wherein said voice characteristics includes a Function A defined as the average or maximum sound volume as a function of sound frequency from within a range of frequencies measured in said sampled period and a Function B defined as the averaging, or maximizing of said function A over said range of frequencies and dyadic multiples thereof;
- c. a database comprising a plurality of reference tones and emotional attitudes corresponding to each of said reference tones for allowing indicating of at least one emotional attitude of said speaker through comparison of said voice characteristics to said reference tones.
Dependencies are inferred from the claim text.