Buffered Media Stream Trigger Word Ignoring for Voice Command Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Voice command devices often mistakenly respond to audio inputs from non-human sources like televisions and radios, leading to erroneous command executions due to the inability to differentiate between human and non-human voice commands.

Innovation Solution

Implementing a system where smart media streaming devices buffer media content and transmit timestamps of upcoming trigger words to voice command devices, allowing them to ignore these words during playback, thereby preventing incorrect command execution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If voice command devices respond to all audio inputs, then they can capture all potential commands, but they mistakenly respond to non-human sources like televisions and radios

Engineering Contradiction:

Improvevoice command responsivenessVSAvoidcommand execution accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary identification of trigger words in the buffered media stream before the media is played. By analyzing the buffer in advance and generating timestamps for upcoming trigger words, the system prepares the voice command device to recognize and ignore these specific audio segments when they are played, preventing erroneous responses while maintaining responsiveness to genuine commands.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system segments the media stream into discrete trigger word instances with specific timestamps. Instead of treating the entire media audio as a single block, the system identifies and marks individual trigger word occurrences at precise time positions, allowing the voice command device to selectively ignore only those specific segments while remaining responsive to other audio inputs.

Inventive Principle:

Principle #1Segmentation

2Reliability

If the system analyzes buffered media stream to identify trigger words, then erroneous responses are reduced, but additional processing time and computational resources are required

Engineering Contradiction:

Improvecommand execution accuracyVSAvoidmedia playback delay

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The trigger word identification and timestamp generation are performed in advance while the media stream is being buffered, before playback begins. This preliminary analysis utilizes the buffering period for processing, so that when playback starts, the system is already prepared with a list of trigger words and their timestamps, eliminating any delay in command execution accuracy during actual playback.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11238856B2Ignoring trigger words in streamed media content

Publication Date: 2022.02.01 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Aspects of the present disclosure relate to ignoring trigger words of a buffered media stream. A buffered media stream of media content is accessed in advance of the playing the media stream. One or more trigger words in the media content of the buffered media stream are identified. A time stamp is generated for each of the one or more identified trigger words in relation to a play time of the media content of the buffered media stream. A voice command device is instructed to ignore audio content of the buffered media stream based on the time stamp for each of the one or more identified trigger words while the buffered media stream is played.