Method and apparatus for recognizing and reacting to user personality in accordance with speech recognition system

• US 9,576,571 B2
• Filed: 05/02/2014
• Issued: 02/21/2017
• Est. Priority Date: 05/18/2006
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Stewart, Osamuyimen Thompson, Dai, Liwei
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US14/268,351
• Publication Number:
  US 20140244260A1
• Time in Patent Office: 1,026 Days
• Field of Search: 704/9, 704/231, 704235-236, 704/251, 704/270, 704/270.1, 434/322, 434/346, 434/353, 434/354, 434/321, 434/236, 434/238, 434/185, 434/178, 434/167, 434/159
• US Class Current: 1/1
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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

Techniques are disclosed for recognizing user personality in accordance with a speech recognition system. For example, a technique for recognizing a personality trait associated with a user interacting with a speech recognition system includes the following steps/operations. One or more decoded spoken utterances of the user are obtained. The one or more decoded spoken utterances are generated by the speech recognition system. The one or more decoded spoken utterances are analyzed to determine one or more linguistic attributes (morphological and syntactic filters) that are associated with the one or more decoded spoken utterances. The personality trait associated with the user is then determined based on the analyzing step/operation.

Claims

1. A method of operating a voice user interface, the method comprising:

customizing, for a user, one or more audio prompts presented to the user via the voice user interface based at least in part on at least one spoken utterance of the user, wherein customizing the one or more audio prompts based at least in part on the analysis comprises;

recognizing a personality trait associated with the user through analysis of the at least one spoken utterance of the user, wherein recognizing the personality trait comprises;

receiving at least one morphological attribute of a plurality of words spoken by the user in the at least one spoken utterance, the at least one morphological attribute comprising a number of compound words that are in the plurality of words; and

determining the personality trait associated with the user based at least in part on the at least one morphological attribute of the plurality of words spoken by the user, wherein the determining comprises determining whether the number of compound words exceeds a threshold; and

selecting, based at least in part on the personality trait, between presenting a first audio prompt or a second audio prompt via the voice user interface; and

outputting the one or more audio prompts, customized for the user, for presentation to the user via the voice user interface.

2. The method of claim 1, further comprising:

receiving the at least one spoken utterance of the user; and

performing automated speech recognition on the at least one spoken utterance.

3. The method of claim 1, further comprising:

receiving at least one syntactic attribute associated with the plurality of words, the at least one syntactic attribute comprising a part of speech in at least one of the plurality of words,

wherein receiving the at least one morphological attribute comprises receiving a number of words that are in the plurality of words, and

wherein determining the personality trait associated with the user further comprises;

determining whether the number of words of the plurality of words exceeds a second threshold value; and

for the part of speech of the at least one of the plurality of words, determining whether a number of occurrences of the part of speech in the plurality of words exceeds a third threshold value associated with the part of speech.

4. The method of claim 1, further comprising:

identifying at least one personality question to be posed to the user, the at least one personality question comprising a first question,

wherein;

the first question of the at least one personality question is associated with a set of expected answers, and

at least some answers, of the set of expected answers associated with the first question, are each associated with a personality trait.

5. The method of claim 4, further comprising:

posing the identified at least one personality question to the user; and

receiving a response to each personality question of the at least one personality question,

wherein determining the personality trait further comprises determining the personality trait based at least in part on the response to each personality question of the at least one personality question.

8. The method of claim 1, further comprising:

following the determining of the personality trait, presenting a dialog to the user via the user interface, wherein the dialog comprises the first audio prompt or the second audio prompt selected based at least in part on the personality trait.

9. The method of claim 2, wherein:

performing the automated speech recognition on the at least one spoken utterance comprises generating the plurality of words, and

the method further comprises analyzing the plurality of words to generate the at least one morphological attribute.

6. At least one non-transitory computer-readable storage medium having encoded thereon executable instructions that, when executed by at least one processor, cause the at least one processor to carry out a method of operating a voice user interface, the method comprising:

customizing, for a user, one or more audio prompts presented to the user via the voice user interface based at least in part on at least one spoken utterance of the user, wherein customizing the one or more audio prompts based at least in part on the analysis comprises;

recognizing a personality trait associated with user through analysis of the at least one spoken utterance of the user, wherein recognizing the personality trait comprises;

receiving at least one morphological attribute of a plurality of words spoken by the user in the at least one spoken utterance, the at least one morphological attribute comprising a number of compound words that are in the plurality of words; and

determining the personality trait associated with the user based at least in part on the at least one morphological attribute of the plurality of words spoken by the user, wherein the determining comprises determining whether the number of compound words exceeds a threshold; and

selecting, based at least in part on the personality trait, between presenting a first audio prompt or a second audio prompt via the voice user interface; and

outputting the one or more audio prompts, customized for the user, for presentation to the user via the voice user interface.

7. An apparatus comprising:

at least one processor; and

at least one computer-readable storage medium having encoded thereon executable instructions that, when executed by the at least one processor, cause the at least one processor to carry out a method operating a voice user interface, the method comprising;

customizing, for a user, one or more audio prompts presented to the user via the voice user interface based at least in part on at least one spoken utterance of the user, wherein customizing the one or more audio prompts based at least in part on the analysis comprises;

recognizing a personality trait associated with the user through analysis of the at least one spoken utterance of the user, wherein recognizing the personality trait comprises;

receiving at least one morphological attribute of a plurality of words spoken by the user in the at least one spoken utterance, the at least one morphological attribute comprising a number of compound words that are in the plurality of words; and

determining the personality trait associated with the user based at least in part on the at least one morphological attribute of the plurality of words spoken by the user, wherein the determining comprises determining whether the number of compound words exceeds a threshold; and

selecting, based at least in part on the personality trait, between presenting a first audio prompt or a second audio prompt via the voice user interface; and

outputting the one or more audio prompts, customized for the user, for presentation to the user via the voice user interface.