Speech Recognition Training for User Voice Isolation in Noise
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-driven systems struggle to distinguish user speech from background speech, particularly in noisy environments with public address systems, leading to potential misinterpretation and interference.
Innovation Solution
A voice-data model is created in a training environment that includes both desired user speech and unwanted background sounds, using human listeners to tag and train a processor-based learning system to differentiate between user and background speech.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If voice-driven systems operate in noisy environments with public address systems, then the system can provide hands-free operation and improve productivity, but the system misinterprets background speech as user speech, reducing reliability
Solution Approach 1:
The system performs preliminary training in a controlled environment where listeners tag and identify user speech versus background speech. This pre-training creates a learned model that enables the system to distinguish between relevant and irrelevant speech in noisy environments during actual operation, resolving the contradiction between hands-free operation capability and speech recognition accuracy
Solution Approach 2:
Human listeners serve as an intermediary between the voice-driven system and the noisy environment. They manually tag and identify user speech versus background speech during training, creating a mediator model that helps the automated system distinguish between relevant commands and irrelevant background noise, thereby improving reliability while maintaining hands-free operation
2Measurement precision
If the system uses machine learning to distinguish user speech from background speech, then speech recognition accuracy improves, but the device complexity increases due to training requirements
Solution Approach 1:
The system creates a simplified copy or model of the complex real-world environment through controlled training sessions. Listeners tag speech samples in a manageable training environment, creating a reduced representation that captures the essence of distinguishing user speech from background noise without requiring the system to handle all environmental complexity directly during operation
Solution Approach 2:
The complex task of distinguishing user speech from background speech in noisy environments is segmented into manageable training components. The training process divides the environment into controlled scenarios where specific types of speech (user vs. background) are identified and tagged separately, making the overall learning process more manageable and systematic
Data Source
AI summary
A device, system, and method whereby a speech-driven system can distinguish speech obtained from users of the system from other speech spoken by background persons, as well as from background speech from public address systems. In one aspect, the present system and method prepares, in advance of field-use, a voice-data file which is created in a training environment. The training environment exhibits both desired user speech and unwanted background speech, including unwanted speech from persons other than a user and also speech from a PA system. The speech recognition system is trained or otherwise programmed to identify wanted user speech which may be spoken concurrently with the background sounds. In an embodiment, during the pre-field-use phase the training or programming may be accomplished by having persons who are training listeners audit the pre-recorded sounds to identify the desired user speech. A processor-based learning system is trained to duplicate the assessments made by the human listeners.