Systems and methods for generating synthesized speech responses to voice inputs by training a neural network model based on the voice input prosodic metrics and training voice inputs
The system provides a synthesized speech response to a voice input, based on the prosodic character of the voice input. The system receives the voice input and calculates at least one prosodic metric of the voice input. The at least one prosodic metric can be associated with a word, phrase, grouping thereof, or the entire voice input. The system also determines a response to the voice input, which may include the sequence of words that form the response. The system generates the synthesized speech response, by determining prosodic characteristics based on the response, and on the prosodic character of the voice input. The system outputs the synthesized speech response, which includes a more natural, relevant, or both answer to the call of the voice input. The prosodic character of the voice input and/or response may include pitch, note, duration, prominence, timbre, rate, and rhythm, for example.
1. A method comprising:
receiving a voice input;
calculating at least one prosodic metric of the voice input;
transmitting the voice input and the at least one prosodic metric to a trained neural network model;
determining a response to the voice input based on the trained neural network model;
generating a synthesized speech response, wherein the synthesized speech response comprises prosodic characteristics based on the response, and on the at least one prosodic metric; and
causing to be output the synthesized speech response.
2. The method of claim 1 , wherein a plurality of reference responses are associated with the voice input, and wherein the prosodic characteristics of the synthesized speech response are further based on a relationship between the at least one prosodic metric and the plurality of reference responses.
3. The method of claim 2 , further comprising identifying which of the plurality of reference responses comprise respective reference prosodic characteristics that are most closely related to the at least one prosodic metric, wherein the prosodic characteristics of the synthesized speech response are further based on the identified reference response.
4. The method of claim 2 , further comprising identifying which of the plurality of reference responses is most closely related to the at least one prosodic metric, wherein the prosodic characteristics of the synthesized speech response are further based on the identified reference response.
5. The method of claim 1 , further comprising determining an emotion metric based on the voice input, wherein the prosodic characteristics are further based on the emotion metric.
6. The method of claim 1 , wherein:
the voice input comprises a plurality of words, and
each prosodic metric of the at least one prosodic metric corresponds to at least one word of the plurality of words.
7. The method of claim 1 , wherein the at least one prosodic metric includes at least one of pitch, note, duration, prominence, timbre, rate, rhythm, or a combination thereof.
8. The method of claim 1 , wherein the generating the synthesized speech response comprises:
determining predicted prosodic characteristics of the response using a model; and
modifying the predicted prosodic characteristics to generate the prosodic characteristics of the synthesized speech response.
9. The method of claim 1 , wherein the prosodic characteristics are further based on at least one of user voice input history, user language, user characteristics, user location, user preferences, or metadata tags associated with the user.
10. The method of claim 1 , wherein the prosodic characteristics are further based on an interpolation operation affecting transitions in the synthesized speech response.
11. A system comprising:
circuitry configured to:
receive a voice input;
calculate at least one prosodic metric of the voice input;
transmit the voice input and the at least one prosodic metric to a neural network model;
determine a response to the voice input based on the neural network model; and
generate a synthesized speech response, wherein the synthesized speech response comprises prosodic characteristics based on the response, and on the at least one prosodic metric; and
an output device configured to output the synthesized speech response.
12. The system of claim 11 , wherein a plurality of reference responses are associated with the voice input, and wherein the prosodic characteristics of the synthesized speech response are further based on a relationship between the at least one prosodic metric and the plurality of reference responses.
13. The system of claim 12 , wherein the circuitry is further configured to identify which of the plurality of reference responses comprise respective reference prosodic characteristics that are most closely related to the at least one prosodic metric, wherein the prosodic characteristics of the synthesized speech response are further based on the identified reference response.
14. The system of claim 12 , wherein the circuitry is further configured to identify which of the plurality of reference responses is most closely related to the at least one prosodic metric, wherein the prosodic characteristics of the synthesized speech response are further based on the identified reference response.
15. The system of claim 11 , wherein the circuitry is further configured to determine an emotion metric based on the voice input, wherein the prosodic characteristics are further based on the emotion metric.
16. The system of claim 11 , wherein:
the voice input comprises a plurality of words, and
each prosodic metric of the at least one prosodic metric corresponds to at least one word of the plurality of words.
17. The system of claim 11 , wherein the at least one prosodic metric includes at least one of pitch, note, duration, prominence, timbre, rate, rhythm, or a combination thereof.
18. The system of claim 11 , wherein the circuitry configured to synthesize the synthesized speech response is further configured to:
determine predicted prosodic characteristics of the response using a model; and
modify the predicted prosodic characteristics to generate the prosodic characteristics of the synthesized speech response.
19. The system of claim 11 , wherein the prosodic characteristics are further based on at least one of user voice input history, user language, user characteristics, user location, user preferences, or metadata tags associated with the user.
20. The system of claim 11 , wherein the prosodic characteristics are further based on an interpolation operation affecting transitions in the synthesized speech response.