Multi-person voice ordering

Abstract

This invention provides a system and method for recognizing utterances from multiple speakers and distinguishing between speakers based on their voices. [Solution] The voice interface recognizes spoken utterances from multiple users, responds to the utterances by changing the attributes of item instances, calculates the voice vector for each utterance, associates it with the item instance to be changed, changes the same instance for subsequent utterances that have a strictly matching voice vector, and changes a different item instance for subsequent utterances that have a voice vector that does not strictly match what is stored for any given item instance.

Claims

1. Receiving a first spoken utterance that specifies the type of item to be changed, The first speech feature vector is calculated from the first spoken utterance, In response to the first spoken utterance, the first item of the specified type is changed, The first audio feature vector is stored in association with the first item, Receiving a second spoken utterance for changing the item of the specified type, The calculation of a second speech feature vector from the second spoken utterance, In response to determining that the second speech feature vector and the first speech feature vector have a difference exceeding a threshold, the second item of the specified type is modified. Outputting an indication of the status of the modified first item and the status of the modified second item, The way a computer performs actions, including [specific actions].

2. The speech feature vector is, Identifying the start of speech activity within audio, The process involves performing automatic speech recognition on the aforementioned audio to recognize words, The completion of the utterance is detected by matching the recognized word with a word pattern, The process involves calculating the speech feature vector as a vector of aggregated speech features in the audio between the start of the speech activity and the completion of the utterance, The method according to claim 1, calculated by...

3. The method according to claim 1, wherein the modification of the second item is performed in response to the second spoken utterance being received within a period of reception of the first spoken utterance, the period being less than 30 seconds.

4. The method according to claim 1, wherein the first item and the second item are members of a list.

5. Determining that the second speech feature vector and the first speech feature vector have a difference exceeding a threshold means that Calculating the distance between points represented by the aforementioned vector in a multidimensional space, It is determined that the second speech feature and the first speech feature vector have a distance exceeding a threshold in the vector space, The method according to claim 1, including the method described in claim 1.

6. Receiving a first spoken utterance specifying the type of item to be ordered or modified, The first speech feature signature is calculated from the first spoken utterance, In response to the first spoken utterance, to order or change the first item of the specified type, The first voice feature signature is stored in association with the first item, Receiving a second spoken utterance for ordering or changing an item of the specified type, The calculation of a second speech feature signature from the second spoken utterance, The second speech feature signature and the first speech feature signature have a difference that exceeds a threshold. In response to the decision, to order or change a second item of the specified type, The way a computer performs actions, including [specific actions].

7. The method according to claim 6, further comprising the step of outputting an indication of the status of the modified first item and the status of the modified second item.

8. The method according to claim 6, wherein the step of calculating a first speech feature signature from the first spoken utterance includes the step of calculating a first speech feature vector from the spoken utterance, and the step of calculating a second speech feature signature from the second spoken utterance includes the step of calculating a second speech feature vector from the second spoken utterance.

9. The speech feature vector is, Identifying the start of speech activity within audio, The process involves performing automatic speech recognition on the aforementioned audio to recognize words, The completion of the utterance is detected by matching the recognized word with a word pattern, The process involves calculating the speech feature vector as a vector of aggregated speech features in the audio between the start of the speech activity and the completion of the utterance, The method according to claim 8, calculated by...

10. Determining that the second speech feature vector and the first speech feature vector have a difference exceeding a threshold means that Calculating the distance between points represented by the aforementioned vector in a multidimensional space, It is determined that the second speech feature and the first speech feature vector have a distance exceeding a threshold in the vector space, The method according to claim 8, including the method described in claim 8.

11. The method according to claim 6, wherein the modification of the second item is performed in response to the second spoken utterance being received within a period of reception of the first spoken utterance, the period being less than 30 seconds.

12. The method according to claim 6, wherein the first item and the second item are members of a list.

13. Calculating a first speech feature signature from a first spoken utterance received, specifying a first item of a specified type to order or change, The first voice feature signature is stored in association with the first item, To calculate a second speech feature signature from a second received spoken utterance for ordering or changing an item of the specified type, In response to determining that the second voice feature signature and the first voice feature signature have a difference exceeding a threshold, order or modify the second item of the specified type. The way a computer performs actions, including [specific actions].

14. The method according to claim 13, further comprising the step of outputting an indication of the status of the modified first item and the status of the modified second item.

15. The step of calculating a first speech feature signature from the first spoken utterance is the The method according to claim 13, comprising the step of calculating a first speech feature vector from a spoken utterance, wherein the step of calculating a second speech feature signature from a second spoken utterance comprises the step of calculating a second speech feature vector from the second spoken utterance.

16. The speech feature vector is, Identifying the start of speech activity within audio, The process involves performing automatic speech recognition on the aforementioned audio to recognize words, The completion of the utterance is detected by matching the recognized word with a word pattern, The process involves calculating the speech feature vector as a vector of aggregated speech features in the audio between the start of the speech activity and the completion of the utterance, The method according to claim 15, calculated by...

17. Determining that the second speech feature vector and the first speech feature vector have a difference exceeding a threshold means that Calculating the distance between points represented by the aforementioned vector in a multidimensional space, It is determined that the second speech feature and the first speech feature vector have a distance exceeding a threshold in the vector space, The method according to claim 15, including the method described in claim 15.

18. The method according to claim 13, wherein the modification of the second item is performed in response to the second spoken utterance being received within a period of reception of the first spoken utterance, the period being less than 30 seconds.

19. The method according to claim 13, wherein the first item and the second item are members of a list.

Images