Systems and methods for disambiguating a voice search query

1. A method comprising:

determining an audio signature of a voice search query, wherein the audio signature comprises a plurality of audio characteristics;

retrieving, in response to the voice search query, metadata of a quotation, wherein the metadata comprises a plurality of audio characteristics characterized by audio signature information corresponding to the quotation and an identifier of a content item comprising the quotation;

comparing the audio signature of the voice search query to the audio signature information in the metadata of the quotation;

determining, based on the comparing, whether a portion of the plurality of audio characteristics of the audio signature of the voice search query match a corresponding portion of the plurality of audio characteristics characterized by the audio signature information; and

in response to determining the portion of the plurality of audio characteristics of the audio signature of the voice search query matches the corresponding portion of the plurality of audio characteristics characterized by the audio signature information, generating for display a search result comprising the identifier of the content item comprising the quotation.

2. The method of claim 1 , wherein the audio signature comprises a plurality of audio characteristics and a plurality of corresponding values for each of the plurality of audio characteristics.

3. The method of claim 2 , wherein the plurality of audio characteristics comprise at least one of a cadence, a spacing of each word spoken relative to other words, a rhythm, and a duration of each word spoken.

4. The method of claim 1 , wherein the plurality of audio characteristics characterized by audio signature information comprises at least one of a cadence, a spacing of each word spoken relative to other words, a rhythm, and a duration of each word spoken.

5. The method of claim 1 , further comprising:

retrieving a similarity threshold value for each of the plurality of audio characteristics, wherein the similarity threshold value corresponds to an allowable difference between a value for each of the plurality of audio characteristics of the audio signature of the voice search query and a value for each of the plurality of audio characteristics characterized by audio signature information corresponding to the quotation;

computing a difference between a value corresponding to the audio signature of the voice search query to a value corresponding to the audio signature information in the metadata of the quotation;

comparing a difference between values corresponding to each of the characteristic the audio signature of the voice search query to a corresponding characteristic of the audio signature information in the metadata of the quotation; and

in response to determining a difference between values corresponding to each of the characteristic the audio signature of the voice search query to the corresponding characteristic of the audio signature information in the metadata of the quotation is the same as or is below the similarity threshold value, determining, based on the comparing, that the audio signature of the voice search query matches the audio signature information corresponding to the quotation.

6. The method of claim 5 , further comprising:

establishing a lower threshold by negatively transposing the audio signature information in the metadata by a predetermined amount;

establishing an upper threshold by positively transposing the audio signature information in the metadata by the predetermined amount; and

determining whether the audio signature of the voice search query is between the lower threshold and the upper threshold.

7. The method of claim 1 , wherein determining, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information comprises:

establishing a lower threshold by negatively modulating cadence information for each word of the voice search query by a predetermined amount;

establishing an upper threshold by positively modulating the cadence information for each word of the voice search query by the predetermined amount; and

determining whether the cadence of each word of the voice search query is between the lower threshold and the upper threshold for a corresponding word of the quotation.

8. The method of claim 1 , wherein determining, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information comprises:

determining a first plurality of relative emphasis levels corresponding to a relative emphasis between each word of the voice search query;

determining a second plurality of relative emphasis levels corresponding to the relative emphasis between each word of the quotation; and

determining, for each relative emphasis level of the first plurality of relative emphasis levels, whether the respective relative emphasis level is within a threshold amount of the corresponding relative emphasis level of the second plurality of emphasis levels.

9. The method of claim 1 , wherein determining, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information comprises:

establishing, for each word of the quotation, a lower threshold duration by reducing the duration information by a predetermined amount;

establishing, for each word of the quotation, an upper threshold duration by increasing the duration information by the predetermined amount; and

determining, for each word of the voice search query, whether the duration of each respective word is between the lower threshold duration and the upper threshold duration for the corresponding word of the quotation.

10. The method of claim 1 , wherein determining, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information comprises:

establishing a lower threshold rhythm by negatively modulating rhythm information corresponding to the quotation by a predetermined amount;

establishing an upper threshold rhythm by positively modulating the rhythm information by the predetermined amount; and

determining whether the overall rhythm of the voice search query is between the lower threshold rhythm and the upper threshold rhythm.

11. A system comprising:

memory; and

control circuitry configured to:

determine an audio signature of a voice search query, wherein the audio signature comprises a plurality of audio characteristics;

retrieve, in response to the voice search query, metadata of a quotation, wherein the metadata comprises a plurality of audio characteristics characterized by audio signature information corresponding to the quotation and an identifier of a content item comprising the quotation;

compare the audio signature of the voice search query to the audio signature information in the metadata of the quotation;

determine, based on the comparing, whether a portion of the plurality of audio characteristics of the audio signature of the voice search query match a corresponding portion of the plurality of audio characteristics characterized by the audio signature information; and

in response to determining the portion of the plurality of audio characteristics of the audio signature of the voice search query matches the corresponding portion of the plurality of audio characteristics characterized by the audio signature information, generate for display a search result comprising the identifier of the content item comprising the quotation.

12. The system of claim 11 , wherein the control circuitry is configured to determine that the audio signature comprises a plurality of audio characteristics and a plurality of corresponding values for each of the plurality of audio characteristics.

13. The system of claim 12 , wherein the control circuitry is further configured to determine the plurality of audio characteristics comprise at least one of a cadence, a spacing of each word spoken relative to other words, a rhythm, and a duration of each word spoken.

14. The system of claim 11 , wherein the control circuitry is further configured to determine the plurality of audio characteristics characterized by audio signature information comprises at least one of a cadence, a spacing of each word spoken relative to other words, a rhythm, and a duration of each word spoken.

15. The system of claim 11 , wherein the control circuitry is further configured to:

retrieve a similarity threshold value for each of the plurality of audio characteristics, wherein the similarity threshold value corresponds to an allowable difference between a value for each of the plurality of audio characteristics of the audio signature of the voice search query and a value for each of the plurality of audio characteristics characterized by audio signature information corresponding to the quotation;

compute a difference between a value corresponding to the audio signature of the voice search query to a value corresponding to the audio signature information in the metadata of the quotation;

compare a difference between values corresponding to each of the characteristic the audio signature of the voice search query to a corresponding characteristic of the audio signature information in the metadata of the quotation; and

in response to determining a difference between values corresponding to each of the characteristic the audio signature of the voice search query to the corresponding characteristic of the audio signature information in the metadata of the quotation is the same as or is below the similarity threshold value, determine, based on the comparing, that the audio signature of the voice search query matches the audio signature information corresponding to the quotation.

16. The system of claim 15 , wherein the control circuitry is further configured to:

establish a lower threshold by negatively transposing the audio signature information in the metadata by a predetermined amount;

establish an upper threshold by positively transposing the audio signature information in the metadata by the predetermined amount; and

determine whether the audio signature of the voice search query is between the lower threshold and the upper threshold.

17. The system of claim 11 , wherein the control circuitry configured to determine, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information is further configured to:

establish a lower threshold by negatively modulating cadence information for each word of the voice search query by a predetermined amount;

establish an upper threshold by positively modulating the cadence information for each word of the voice search query by the predetermined amount; and

determine whether the cadence of each word of the voice search query is between the lower threshold and the upper threshold for a corresponding word of the quotation.

18. The system of claim 11 , wherein the control circuitry configured to determine, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information is further configured to:

determine a first plurality of relative emphasis levels corresponding to a relative emphasis between each word of the voice search query;

determine a second plurality of relative emphasis levels corresponding to the relative emphasis between each word of the quotation; and

determine, for each relative emphasis level of the first plurality of relative emphasis levels, whether the respective relative emphasis level is within a threshold amount of the corresponding relative emphasis level of the second plurality of emphasis levels.

19. The system of claim 11 , wherein the control circuitry configured to determine, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information is further configured to:

establish, for each word of the quotation, a lower threshold duration by reducing the duration information by a predetermined amount;

establish, for each word of the quotation, an upper threshold duration by increasing the duration information by the predetermined amount; and

determine, for each word of the voice search query, whether the duration of each respective word is between the lower threshold duration and the upper threshold duration for the corresponding word of the quotation.

20. The system of claim 11 , wherein the control circuitry configured to determine, based on the comparing, whether the portion of the plurality of audio characteristics of the audio signature of the voice search query match the corresponding portion of the plurality of audio characteristics characterized by the audio signature information is further configured to:

establish a lower threshold rhythm by negatively modulating rhythm information corresponding to the quotation by a predetermined amount;

establish an upper threshold rhythm by positively modulating the rhythm information by the predetermined amount; and

determine whether the overall rhythm of the voice search query is between the lower threshold rhythm and the upper threshold rhythm.