Full-Duplex Voice Control for Music Playback Continuity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current voice control systems for intelligent devices require users to wake up the device for each interaction, which complicates operations and disrupts ongoing tasks, such as music playback, leading to a poor user experience.

Innovation Solution

Implementing a full-duplex listening state for a predetermined period after entering a music mode allows the device to recognize and execute voice commands without wake-up words, ensuring continuous operation and improved user experience by maintaining music playback without interrupting it.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the device requires wake-up operation for each voice interaction, then the device can accurately recognize user commands, but the operation complexity increases and ongoing tasks are interrupted

Engineering Contradiction:
Improvevoice command recognition accuracyVSAvoidoperation complexity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The device performs preliminary action by entering a music mode that automatically activates a listening state before voice command recognition is needed. This preliminary setup eliminates the need for separate wake-up operations, allowing users to directly issue voice commands during music playback without additional operational steps.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The listening state maintained during music mode enables continuous voice command recognition without interrupting the music playback. The device continuously processes both music output and voice input simultaneously, ensuring the useful action of music playback continues uninterrupted while maintaining readiness for voice commands.

Inventive Principle:
Principle #20Continuity of useful action

2Measurement precision

If the device enters wake-up state for voice interaction, then voice commands can be recognized, but the current operation state is stopped

Engineering Contradiction:
Improvevoice command recognitionVSAvoidmusic playback continuity
Core Design Contradiction:
Measurement precisionVSDuration of action of stationary object

Solution Approach 1:

The music mode is designed to maintain continuous music playback while simultaneously maintaining an active listening state for voice commands. The device architecture allows both functions to operate concurrently without one interrupting the other, ensuring music playback duration is not reduced by voice interaction requirements.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The device preliminarily enters a listening state when music mode is activated, before any voice command is issued. This preliminary preparation ensures that when users speak during music playback, the device is already ready to recognize commands without needing to transition from music playback to a wake-up state, thus maintaining continuous operation.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If wake-up operation is required for each interaction, then the device can process voice commands, but user cost and time increase

Engineering Contradiction:
Improvevoice command processingVSAvoidinteraction time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The listening state persists continuously during music mode without requiring periodic wake-up operations. Users can issue multiple voice commands during music playback without repeated wake-up delays, reducing the time lost to interaction overhead and making the voice processing system more efficient for continuous use.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The device preliminarily activates the listening capability when music mode starts, eliminating the need for repeated wake-up actions during the music session. This preliminary activation reduces the time users would otherwise spend on wake-up operations, allowing immediate voice command processing throughout the music playback duration.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3745253B1Voice control methods and apparatuses for electronic device, computer devices, and storage media
Publication Date: 2023.10.04 BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
  • EP3745253B1 patent drawingFigure 1
  • EP3745253B1 patent drawingFigure 2
  • EP3745253B1 patent drawingFigure 3~5

AI summary

The present disclosure provides a voice control method, a computer device, and a storage medium. The method includes: launching a full-duplex listening state of an electronic device in response to that the electronic device enters a music mode; acquiring a user command; and executing the user command in a case that the user command is relevant to the music mode.