Emotion-Adaptive Voice Interface Synchronous Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice interfaces fail to adequately respond to user emotions in utterances, leading to insensitive or delayed reactions, and often neglect past emotional interactions, frustrating users and reducing interaction efficiency.

Innovation Solution

The system processes natural and synthesized utterances by extracting emotion features from vocal cues, mapping them to user-specific emotions, and adapting responses to include both command acknowledgments and actions, even when commands are unintelligible, by performing synchronous language and emotion processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the system processes both language and emotion to improve response quality, then the response becomes more emotionally sensitive and personalized, but the processing time increases causing delays

Engineering Contradiction:
Improveresponse qualityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system divides the processing task into two independent parallel streams: language processing and emotion processing. Each stream handles its specific aspect independently, allowing simultaneous execution without sequential delays. The language processor extracts commands and intent while the emotion processor analyzes emotional content, both feeding into the response generation system concurrently.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary emotion detection and analysis concurrently with language processing rather than sequentially. By initiating emotion feature extraction and mapping operations at the same time as command extraction, the system prepares emotional context information in advance, eliminating waiting time and enabling immediate integration into the response generation phase.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the system extracts and processes emotion features from utterances, then the response becomes emotionally aware and adaptive, but the system complexity increases

Engineering Contradiction:
Improveemotional adaptabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The emotion processing module serves multiple functions within the voice interface system: detecting emotional states, mapping emotions to user-specific profiles, adapting response tone and style, and informing command interpretation. This multi-functional approach consolidates what could be separate complex subsystems into a unified emotion processing component.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an emotion feature extraction and mapping module as an intermediary between raw utterance input and response generation. This intermediary layer translates complex acoustic and spectral features into simplified emotional labels and user-specific emotion representations, making the emotion information accessible and actionable for the response system without requiring direct complex analysis at every stage.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If the system responds to emotions in real-time, then user satisfaction improves, but the processing speed may decrease

Engineering Contradiction:
Improveuser satisfactionVSAvoidresponse speed
Core Design Contradiction:
ReliabilityVSSpeed

Solution Approach 1:

The system performs partial emotion processing by extracting key emotional features and mapping them to predefined emotion categories rather than conducting exhaustive emotional analysis. This selective approach processes only the most salient emotional indicators necessary for adapting the response, avoiding unnecessary computational overhead while maintaining user satisfaction through emotionally appropriate responses.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3557577B1Systems and methods for enhancing responsiveness to utterances having detectable emotion
Publication Date: 2022.09.21 SPOTIFY
  • EP3557577B1 patent drawingFigure 1
  • EP3557577B1 patent drawingFigure 2
  • EP3557577B1 patent drawingFigure 3

AI summary

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 synchronously.