Wearable Vibrotactile Speech Aid Using Envelope Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies do not effectively enable speech recognition through vibrotactile means without supplementary auditory or visual cues, limiting the ability of individuals to perceive speech solely through haptic sensations.
Innovation Solution
A wearable vibrotactile speech aid device that samples speech signals, extracts a speech envelope, and generates control signals to cause vibrotactile transducers to vibrate, allowing for improved speech recognition by converting auditory signals into haptic sensations, which can supplement or replace aural and visual speech recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If auditory signals are converted into haptic signals for speech recognition, then speech perception is enabled for individuals with hearing impairments, but the complexity of the device increases
Solution Approach 1:
The speech signal is segmented into frequency bands using a spectrogram analysis, with different vibrotactile transducers handling different frequency ranges. This segmentation allows complex speech information to be distributed across multiple simpler transducer channels, enabling speech perception while managing device complexity through functional decomposition
Solution Approach 2:
The patent introduces an intermediary processing system that converts auditory signals into haptic patterns through envelope extraction and spectrogram generation. This intermediary layer transforms the signal representation form without requiring direct mechanical conversion, enabling speech perception through a mediating computational process rather than complex direct transduction
2Measurement precision
If multiple vibrotactile transducers are used to represent different frequency bands, then speech recognition accuracy improves, but the device complexity and size increase
Solution Approach 1:
Different vibrotactile transducers are assigned to different frequency bands of the speech signal, with each transducer optimized for its specific frequency range. This local quality assignment allows accurate representation of various speech components across the frequency spectrum while keeping each individual transducer's function simple and well-defined
Solution Approach 2:
The patent transforms the one-dimensional temporal speech signal into a two-dimensional spectrogram representation (frequency vs. time), which is then mapped to multiple transducers. This dimensional transformation allows speech recognition accuracy to improve by distributing information across frequency channels while managing complexity through structured organization of the additional dimension
3Measurement precision
If the speech envelope is extracted using complex methods like Hilbert transform, then speech recognition accuracy improves, but the processing time and computational load increase
Solution Approach 1:
The patent extracts only the essential envelope information from the speech signal rather than processing the complete spectral content in real-time. By focusing on the amplitude envelope which contains the primary speech intelligibility information, the system achieves sufficient recognition accuracy while reducing computational load and processing time compared to full spectral analysis
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
The device enhances speech recognition capabilities by allowing individuals to learn and interpret vibration patterns, improving recognition in noisy environments and for individuals with hearing impairments, and enables speech perception without relying on auditory signals.
Implementation Method 1
generating a control signal configured to cause one or more vibrotactile transducer to vibrate against a person's body
Data Source
AI summary
A method for training vibrotactile speech perception in the absence of auditory speech includes selecting a first word, generating a first control signal configured to cause at least one vibrotactile transducer to vibrate against a person's body with a first vibration pattern based on the first word, sampling a second word spoken by the person, generating a second control signal configured to cause at least one vibrotactile transducer to vibrate against the person's body with a second vibration pattern based on the sampled second word, and presenting a comparison between the first word and the second word to the person. An array of vibrotactile transducers can be in contact with the person's body. A method for improving auditory and/or visual speech perception in adverse listening conditions or for hearing-impaired individuals can also include sampling a speech signal, extracting a speech envelope, and generating a control signal configured to cause a vibrotactile transducer to vibrate again a person's body with an intensity that varies over time based on the speech envelope.