Systems and Methods for Enhancing Responsiveness to Utterances Having Detectable Emotion

• US 20190325895A1
• Filed: 04/20/2018
• Published: 10/24/2019
• Est. Priority Date: 04/20/2018
• Status: Active Grant

• Current Assignee: Spotify AB (Spotify Technology SA)
• Original Assignee: Spotify AB (Spotify Technology SA)
• Inventors: BROMAND, Daniel, GUSTAFSSON, David, MITIC, Richard, MENNICKEN, Sarah
• Granted Patent: US 10,622,007 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

Methods, systems, and related products that provide emotion-sensitive responses to user'"'"'s commands and other utterances received at an utterance-based user interface. Acknowledgements of user'"'"'s utterances are adapted to the user and/or the user device, and emotions detected in the user'"'"'s utterance that have been mapped from one or more emotion features extracted from the utterance. In some examples, extraction of a user'"'"'s changing emotion during a sequence of interactions is used to generate a response to a user'"'"'s uttered command. In some examples, emotion processing and command processing of natural utterances are performed asynchronously.

Claims

1. A method comprising:

receiving, via a user device, a natural utterance;

converting the natural utterance into text;

extracting a textual emotion feature from the text;

extracting a non-textual emotion feature from the natural utterance, the textual emotion feature and the non-textual emotion feature corresponding to conflicting first and second commands;

selecting either the non-textual emotion feature or the textual emotion feature, thereby providing a selected emotion feature;

mapping the selected emotion feature to an emotion; and

responding to the natural utterance by providing a verbalized acknowledgement of the natural utterance adapted to the emotion and performing an action corresponding to the command associated with the selected emotion feature.

3. The method of claim 1, wherein the verbalized acknowledgement comprises a synthesized utterance.

4. The method of claim 3, wherein the synthesized utterance is adapted to the emotion with at least one audible stylization, the at least one audible stylization being one or more of a cadence, a volume, a pitch, a word, a string of words, a pace, and a tone.

5. The method of claim 1, wherein the verbalized acknowledgement comprises a displayed text.

6. The method of claim 5, wherein the displayed text is adapted to the emotion with at least one visual stylization, the at least one visual stylization being one or more of a font type, a font size, a font color, capital letters, a number of words, and a punctuation mark.

7. The method of claim 1, wherein each of the non-textual emotion feature and textual emotion feature includes one or more of a cadence, a volume, a pitch, a word, a string of words, a pace, and a tone.

8. The method of claim 1, wherein the mapping is partially based on an identity of a user.

9. The method of claim 1, wherein a type of the verbalized acknowledgement is based on a type of the user device.

10. The method of claim 9,

wherein the user device comprises an automobile, and

wherein the type of the verbalized acknowledgement is a synthesized utterance.

11. The method of claim 1, wherein the verbalized acknowledgement comprises a reflector of the command associated with the selected emotion feature.

12. The method of claim 11, wherein the reflector comprises a conjugated form of a word in the command associated with the selected emotion feature.

2. (canceled)

13-14. -14. (canceled)

15. A non-transitory computer readable medium comprising:

an emotion processor having one or more sequences of emotion processor instructions that, when executed by one or more processors, causes the one or more processors to generate an output adapted to an emotion detected in a natural utterance;

and one or more sequences of instructions which, when executed by one or more processors, cause the one or processors to;

receive the natural utterance,

convert the natural utterance into text;

extract a textual emotion feature from the text;

extract a non-textual emotion feature from the natural utterance, the textual emotion feature and the non-textual emotion feature corresponding to conflicting first and second commands;

select either the non-textual emotion feature or the textual emotion feature, thereby providing a selected emotion feature;

map the selected emotion feature to an emotion; and

respond to the natural utterance by providing a verbalized acknowledgement adapted to the emotion and performing an action corresponding to the command associated with the selected emotion feature.

16. A method comprising:

receiving, via a user device, a natural utterance, the natural utterance including a command and at least one emotion feature;

extracting the command;

extracting the at least one emotion feature from the natural utterance;

mapping each of the at least one emotion feature to an emotion; and

responding to the natural utterance at least by providing a verbalized acknowledgement of the natural utterance adapted to the emotion,

wherein a type of the verbalized acknowledgement is based on a type of the user device.

17. The method of claim 16,

wherein the user device comprises an automobile;

and

wherein the type of the verbalized acknowledgement is a synthesized utterance.