Voice Command Noise Cancellation in Content Reproduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The accuracy of voice interaction is compromised when using voice commands during content reproduction, as the voice in the content is often misinterpreted as noise, leading to deterioration in interaction accuracy.

Innovation Solution

A system that captures audio data containing voice commands, identifies and separates it from background noise within the content, converts the voice command data to text, and outputs the text for processing, thereby improving interaction accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice interaction is used during content reproduction, then ease of operation is improved, but measurement precision deteriorates due to voice noise in the content

Engineering Contradiction:

Improveease of operationVSAvoidaccuracy of voice interaction

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent extracts and removes the voice noise from the content audio data to create a noise-free version. This extracted noise is then used to generate a noise cancellation signal that is subtracted from the original audio data, effectively separating the user's voice command from the content voice noise.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediary noise cancellation signal that is generated by processing the voice noise from the content. This intermediary signal acts as a mediator between the noisy audio data and the clean voice command, enabling accurate recognition by canceling out the interfering noise.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If audio data is captured during content reproduction, then productivity is improved, but measurement precision deteriorates due to background noise

Engineering Contradiction:

ImproveproductivityVSAvoidaccuracy of voice command recognition

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent converts the harmful voice noise from the content into a beneficial cancellation signal. By first capturing and analyzing the noise characteristics, the system generates a cancellation signal that actively removes the noise, turning the previously harmful interference into a useful tool for noise reduction.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent implements feedback by continuously monitoring the audio data, identifying noise patterns, and generating cancellation signals based on this feedback. The system adjusts the noise cancellation process based on the captured audio characteristics, improving accuracy over time.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11227620B2Information processing apparatus and information processing method

Publication Date: 2022.01.18 SATURN LICENSING LLC

AI summary

A system that acquires first audio data including a voice command captured by a microphone; identifies second audio data included in broadcast content corresponding to a timing at which the first audio data is captured by the microphone; extracts the second audio data from the first audio data to generate third audio data; converts the third audio data to text data corresponding to the voice command; and outputs the text data.