Resolving pronoun ambiguity in voice queries

• US 10,019,434 B1
• Filed: 12/21/2016
• Issued: 07/10/2018
• Est. Priority Date: 06/01/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Taubman, Gabriel, Lee, John J.
• Primary Examiner(s): Patel, Shreyans
• Application Number:
  US15/386,113
• Time in Patent Office: 566 Days
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving ambiguity in received voice queries. An original voice query is received following one or more earlier voice queries, wherein the original voice query includes a pronoun or phrase. In one implementation, a plurality of acoustic parameters is identified for one or more words in the original voice query. A concept represented by the pronoun is identified based on the plurality of acoustic parameters, wherein the concept is associated with a particular query of the one or more earlier queries. The concept is associated with the pronoun. Alternatively, a concept may be associated with a phrase by using grammatical analysis of the query to relate the phrase to a concept derived from a prior query.

Claims

1. A computer-implemented method, comprising:

receiving multiple search queries;

identifying, for each search query of the received search queries, an entity associated with (i) the search query or (ii) a pair comprising the search query and an answer that a search engine generates in response to the search query;

after receiving the search queries, receiving a voice query that includes a pronoun;

identifying a plurality of acoustic parameters associated with the pronoun, wherein the identified plurality of acoustic parameters comprise two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters associated with the pronoun comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

modifying the voice query based at least on the selected entity; and

obtaining an answer that the search engine generates in response to the modified search query.

2. The method of claim 1, comprising:

determining a stress score for the pronoun based at least on the identified plurality of acoustic parameters.

3. The method of claim 2, wherein selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases comprises:

selecting the particular entity based at least on the stress score for the pronoun.

4. The method of claim 3, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold;

and

in response to determining that the stress score for the pronoun satisfies the predetermined threshold, selecting a most recently identified entity.

5. The method of claim 3, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold; and

in response to determining that the stress score for the pronoun does not satisfy the predetermined threshold, selecting an entity identified before a most recently identified entity.

6. The method of claim 1, wherein selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases further comprises:

selecting the particular entity based on a gender that the pronoun references.

7. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving multiple search queries;

identifying, for each search query of the received search queries, an entity associated with (i) the search query or (ii) a pair comprising the search query and an answer that a search engine generates in response to the search query;

after receiving the search queries, receiving a voice query that includes a pronoun;

identifying a plurality of acoustic parameters associated with the pronoun, wherein the identified plurality of acoustic parameters include two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters associated with the pronoun comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

modifying the voice query based at least on the selected entity; and

obtaining an answer that the search engine generates in response to the modified search query.

8. The system of claim 7, the operations comprising:

determining a stress score for the pronoun based at least on the identified plurality of acoustic parameters.

9. The system of claim 8, wherein selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases comprises:

selecting the particular entity based at least on the stress score for the pronoun.

10. The system of claim 9, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold;

and

in response to determining that the stress score for the pronoun satisfies the predetermined threshold, selecting a most recently identified entity.

11. The system of claim 9, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold; and

in response to determining that the stress score for the pronoun does not satisfy the predetermined threshold, selecting an entity identified before a most recently identified entity.

12. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving multiple search queries;

identifying, for each search query of the received search queries, an entity associated with (i) the search query or (ii) a pair comprising the search query and an answer that a search engine generates in response to the search query;

after receiving the search queries, receiving a voice query that includes a pronoun;

identifying a plurality of acoustic parameters associated with the pronoun, wherein the identified plurality of acoustic parameters include two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters associated with the pronoun comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases;

modifying the voice query based at least on the selected entity; and

obtaining an answer that the search engine generates in response to the modified search query.

13. The computer-readable medium of claim 12, the operations comprising:

determining a stress score for the pronoun based at least on the identified plurality of acoustic parameters.

14. The computer-readable medium of claim 13, wherein selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases comprises:

selecting the particular entity based at least on the stress score for the pronoun.

15. The computer-readable medium of claim 14, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold;

and

in response to determining that the stress score for the pronoun satisfies the predetermined threshold, selecting a most recently identified entity.

16. The computer-readable medium of claim 14, wherein selecting the particular entity based at least on the stress score for the pronoun comprises:

determining whether the stress score for the pronoun satisfies a predetermined threshold; and

in response to determining that the stress score for the pronoun does not satisfy the predetermined threshold, selecting an entity identified before a most recently identified entity.

17. The computer-readable medium of claim 12, wherein selecting, from among the identified entities associated with (i) the search queries or (ii) the pairs that each comprise a search query and an answer that a search engine generates in response to the search query, a particular entity based at least on the identified plurality of acoustic parameters comprising two or more of volume, pitch, frequency, duration between each spoken word, and spoken duration of words or phrases further comprises:

selecting the particular entity based on a gender that the pronoun references.