Silent Voice Input Using Ingressive Airflow
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice input is underutilized in public and mobile settings due to potential disturbance and leakage of private information, as conventional voice input methods rely on egressive airflow, causing noise and discomfort to others.
Innovation Solution
A silent voice input method utilizing ingressive airflow, captured by a microphone placed close to the user's mouth with a small gap, allowing for ultra-low volume speech input without disturbing others, using a microphone and flow sensor to differentiate between ingressive and egressive airflow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional voice input methods using egressive airflow are used, then voice recognition can be achieved, but noise leakage disturbs surrounding people and compromises privacy
Solution Approach 1:
The patent inverts the conventional egressive airflow approach by using ingressive airflow (breathing in) to generate voice signals. The microphone captures sound waves generated during inhalation, which naturally produces lower volume and less noise leakage compared to exhalation-based speech, thus resolving the contradiction between recognition accuracy and noise leakage
Solution Approach 2:
The patent changes the airflow direction parameter from egressive to ingressive, fundamentally altering how voice signals are generated. This parameter change results in different acoustic characteristics that reduce noise leakage while maintaining speech intelligibility for recognition
2Reliability
If the microphone is placed close to the user's mouth to capture stable utterance signal, then voice input reliability improves, but voice leakage to surrounding areas increases
Solution Approach 1:
By inverting to using ingressive airflow, the system can place the microphone close to the mouth to capture stable signals while the inhalation-based sound generation naturally limits voice leakage to surrounding areas, resolving the spatial positioning contradiction
3Object-generated harmful factors
If whispering is used to reduce noise, then voice leakage is reduced, but recognition accuracy deteriorates
Solution Approach 1:
Instead of whispering (which uses egressive airflow), the patent uses ingressive airflow to generate voice signals. This inversion maintains sufficient sound energy for accurate recognition while naturally reducing voice leakage, as inhalation-based sounds are less likely to propagate to surrounding areas
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
Enables undetectable voice input in public and mobile scenarios, reducing noise leakage and maintaining privacy, while maintaining recognition accuracy through proper acoustic modeling and signal processing.
Implementation Method 1
detecting a sound generated by the user during the ingressive utterance
Implementation Method 2
using a microphone and flow sensor to differentiate between ingressive and egressive airflow
Data Source
Figure 1~2B
Figure 3A~3D
Figure 4A~5
AI summary
Implementations of the subject matter described herein provide a silent voice input solution without being noticed by surroundings. Compared with conventional voice input solutions which are based on normal speech or whispering, the proposed "silent" voice input method is performed by using ingressive voice during the user's breathing-in process. By placing the apparatus(10) very close to the user's mouth with a ultra-small gap (110) formed between the microphone (100) and the apparatus (10), the proposed silent voice input solution can realize a very small voice leakage, and thereby allowing the user (1000) to use ultra-low voice speech input in public and mobile situations, without disturbing surrounding people.