Methods, apparatuses and computer program products for implementing automatic speech recognition and sentiment detection on a device

• US 8,930,187 B2
• Filed: 01/03/2012
• Issued: 01/06/2015
• Est. Priority Date: 01/03/2012
• Status: Active Grant

• Current Assignee: Piece Future Pte., Ltd.
• Original Assignee: Nokia Corporation
• Inventors: Kiss, Imre Attila, Polifroni, Joseph, Mairesse, Francois, Adler, Mark
• Primary Examiner(s): SAINT CYR, LEONARD
• Application Number:
  US13/342,534
• Publication Number:
  US 20130173264A1
• Time in Patent Office: 1,099 Days
• Field of Search: 704/246, 704/247, 704/251, 704/252, 704/257
• US Class Current: 704/231
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

An apparatus for utilizing textual data and acoustic data corresponding to speech data to detect sentiment may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including evaluating textual data and acoustic data corresponding to voice data associated with captured speech content. The computer program code may further cause the apparatus to analyze the textual data and the acoustic data to detect whether the textual data or the acoustic data includes one or more words indicating at least one sentiment of a user that spoke the speech content. The computer program code may further cause the apparatus to assign at least one predefined sentiment to at least one of the words in response to detecting that the word(s) indicates the sentiment of the user. Corresponding methods and computer program products are also provided.

Claims

1. A method comprising:

evaluating textual data and acoustic data corresponding to voice data associated with captured speech content;

analyzing the textual data and the acoustic data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content;

assigning, via a processor, at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user, wherein the at least one assigned predefined sentiment corresponds to at least one attribute of a domain;

generating at least one rating based in part on a classification of the predefined sentiment, the rating denotes an opinion regarding the attribute relating to an entity; and

generating a review indicating the rating.

2. The method of claim 1, wherein the textual data comprises textual words and the acoustic data comprises spoken words and wherein assigning the at least one predefined sentiment comprises assigning a textual sentiment to the at least one word and an acoustic sentiment to the at least one word, wherein the at least one sentiment of the user denotes at least one opinion of the user.

3. The method of claim 2, further comprising:

combining the textual sentiment and the acoustic sentiment to determine a composite sentiment associated with the at least one word.

4. The method of claim 3, further comprising:

determining a confidence associated with the composite sentiment, the confidence indicating a measure of accuracy relating to the composite sentiment.

5. The method of claim 1, wherein assigning the at least one predefined sentiment comprises classifying the word according to a plurality of sentiment classifications that are associated with a determined confidence score and wherein the method further comprises:

determining that the assigned predefined sentiment corresponds to the sentiment classification that comprises a highest confidence score.

6. The method of claim 1, further comprising:

enabling provision of the generated review to one or more devices.

7. The method of claim 1, wherein prior to evaluating the textual data and the acoustic data, the method further comprises converting the speech data to the textual data and wherein the speech data corresponds to a spoken review of the user relating to an entity.

8. The method of claim 1, wherein generating the review further comprises generating the review based in part on a spoken review of the user relating to the entity,

wherein the opinion comprises an opinion of the user.

9. An apparatus comprising:

at least one processor; and

at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following;

evaluate textual data and acoustic data corresponding to voice data associated with captured speech content;

analyze the textual data and the acoustic data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content;

assign at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user, wherein the at least one assigned predefined sentiment corresponds to at least one attribute of a domain;

generate at least one rating based in part on a classification of the predefined sentiment, the rating denotes an opinion regarding the attribute relating to an entity; and

generate a review indicating the rating.

10. The apparatus of claim 9, wherein the textual data comprises textual words and the acoustic data comprises spoken words and wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

assign the at least one predefined sentiment by assigning a textual sentiment to the at least one word and an acoustic sentiment to the at least one word, wherein the at least one sentiment of the user denotes at least one opinion of the user.

11. The apparatus of claim 10, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

combine the textual sentiment and the acoustic sentiment to determine a composite sentiment associated with the at least one word.

12. The apparatus of claim 11, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

determine a confidence associated with the composite sentiment, the confidence indicating a measure of accuracy relating to the composite sentiment.

13. The apparatus of claim 9, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

assign the at least one predefined sentiment by classifying the word according to a plurality of sentiment classifications that are associated with a determined confidence score; and

determine that the assigned predefined sentiment corresponds to the sentiment classification that comprises a highest confidence score.

14. The apparatus of claim 9, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

enable provision of the generated review to one or more devices.

15. The apparatus of claim 9, wherein prior to evaluate the textual data and the acoustic data, the memory and computer program code are configured to, with the processor, cause the apparatus to:

convert the speech data to the textual data and wherein the speech data corresponds to a spoken review of the user relating to an entity.

16. The apparatus of claim 9, wherein the memory and computer program code are configured to, with the processor, cause the apparatus to:

generate the review by generating the review based in part on a spoken review of the user relating to the entity,

wherein the opinion comprises an opinion of the user.

17. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions in response to execution by a processor causes an apparatus to at least:

evaluate textual data and acoustic data corresponding to voice data associated with captured speech content;

analyze textual data and the acoustic data to detect whether the textual data or the acoustic data comprises one or more words indicating at least one sentiment of a user that spoke the speech content;

assign at least one predefined sentiment to at least one of the words in response to detecting that the word indicates the sentiment of the user, wherein the at least one assigned predefined sentiment corresponds to at least one attribute of a domain;

generate at least one rating based in part on a classification of the predefined sentiment, the rating denotes an opinion regarding the attribute relating to an entity; and

generate a review indicating the rating.

18. The computer program product of claim 17, wherein the textual data comprises textual words and the acoustic data comprises spoken words and wherein assign the at least one predefined sentiment further comprises assigning a textual sentiment to the at least one word and an acoustic sentiment to the at least one word, wherein the at least one sentiment of the user denotes at least one opinion of the user.

19. The computer program product of claim 18, wherein the computer-readable program code portions in response to execution by the processor further causes the apparatus to:

combine the textual sentiment and the acoustic sentiment to determine a composite sentiment associated with the at least one word.

20. The computer program product of claim 17, wherein assign the at least one predefined sentiment comprises classifying the word according to a plurality of sentiment classifications that are associated with a determined confidence score and wherein the computer-readable program code portions in response to execution by the processor further causes the apparatus to:

determine that the assigned predefined sentiment corresponds to the sentiment classification that comprises a highest confidence score.