Adaptive Talk-Back Cancellation in Voice Recognition Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems require users to wait until a talk-back operation is finished before inputting voice commands, leading to increased operation time and complexity, especially when multiple levels of voice input are needed, due to the inability to input voice during talk-back operations.
Innovation Solution
A voice recognition system that uses adaptive filters to simulate and subtract talk-back voices from microphone input, allowing continuous voice input during talk-back operations by estimating and filtering out the talk-back voice, thereby enabling voice input at any time without interrupting the talk-back process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system outputs talk-back voice through the speaker, then the user can check recognition accuracy, but the user cannot input voice during the talk-back operation, increasing recognition time
Solution Approach 1:
The patent extracts the talk-back voice signal from the microphone input by generating a simulated talk-back voice through adaptive filtering and subtracting it from the actual microphone signal. This separation allows the system to isolate and process only the user's input voice, enabling continuous voice input acceptance during talk-back operations without interference.
Solution Approach 2:
The adaptive filter acts as an intermediary that generates a simulated talk-back voice signal based on the speaker output and microphone characteristics. This intermediary signal serves as a reference that can be subtracted from the actual microphone input, effectively removing the talk-back voice component and allowing simultaneous voice input processing.
2Ease of operation
If the user presses the speech button multiple times to input voice for each level, then voice input can be completed, but the operation becomes very complicated
Solution Approach 1:
The patent enables continuous voice input processing during talk-back operations by removing the talk-back voice component from the microphone signal. The system continuously accepts and processes user voice inputs without requiring interruption or additional button presses, maintaining uninterrupted voice command input flow for multi-level commands.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution reduces voice recognition operation time by allowing users to input voice commands without waiting for the talk-back operation to finish, simplifying the process and eliminating the need to repeatedly press a speech button, while enhancing talk-back voice articulation and reducing costs.
Implementation Method 1
an adaptive filter unit for generating a simulated talk-back voice inputted into the microphone by setting a filter coefficient simulating a transfer system in which the talk-back voice outputted from the speaker is inputted into the microphone
Implementation Method 2
an input-voice extracting unit for extracting the input voice by subtracting the simulated talk-back voice from sound inputted into the microphone
Data Source
AI summary
A voice recognition system includes an adaptive filter and a subtractor. The adaptive filter generates a simulated talk-back voice y(n) by setting a filter coefficient simulating a transfer system in which an input voice corresponding to a voice command and a talk-back voice output from a speaker are input into a microphone and by filtering a talk-back voice x(n). The subtractor extracts the input voice by subtracting the simulated talk-back voice y(n) from mixed sound input into the microphone. With this configuration, the talk-back voice is attenuated from the mixed sound including the input voice and the talk-back voice input tedinto the microphone, and then, the mixed sound is supplied to a voice recognition engine. Accordingly, the user can input his/her voice during a talk-back operation without the need to interrupt it by pressing a speech button every time the user wishes to input the voice. The voice recognition operation time can be thus reduced.