Related Experiment Video
Updated: Jul 3, 2026
11:54
Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
Published on: May 8, 2021
SNR-adaptive stream weighting for audio-MES ASR.
1Department of Electronic Engineering, Konkuk University, Seoul 143-701, Korea. kseung@konkuk.ac.kr
IEEE Transactions on Bio-Medical Engineering
|July 18, 2008
Summary
Myoelectric signals (MESs) from the mouth improve automatic speech recognition (ASR) in noisy environments. Integrating audio and MES features with adaptive weighting significantly boosts classification accuracy, outperforming audio-only ASR.
Area of Science:
- Speech processing
- Biomedical engineering
- Machine learning
Background:
- Automatic speech recognition (ASR) systems struggle with noise robustness.
- Myoelectric signals (MESs) from the mouth region offer a potential solution for noise-robust ASR.
Purpose of the Study:
- To integrate audio and facial MES features for improved ASR performance.
- To develop an adaptive weighting method for optimal feature fusion based on signal-to-noise ratio (SNR).
- To determine optimal SNR classification boundaries and stream weights using a maximum mutual information criterion.
Main Methods:
- Feature extraction from audio and facial MES data.
- Decision fusion of audio and MES features using a weighted linear combination of likelihoods.
- Development of an SNR-adaptive weighting process.
- Optimization of SNR classification boundaries and stream weights via maximum mutual information.
Main Results:
- MES-based ASR achieved 85.2% accuracy, significantly higher than audio-only ASR (25.5%).
- The proposed audio-MES weighting method further improved accuracy to 89.4% in babble noise.
- Consistent improvements were observed across various noise types (babble, car, aircraft, white noise).
Conclusions:
- Integrating audio and facial MES features enhances ASR noise robustness.
- SNR-adaptive weighting is effective for optimizing feature fusion in noisy conditions.
- The proposed method offers a promising approach for developing highly reliable ASR systems for real-world applications.
Related Concept Videos
01:22Upsampling
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
01:18Aliasing
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original signal...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original signal...
01:20Downsampling
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
01:29Downstream Processing
Downstream processing begins once fermentation is complete and involves a series of steps to recover and purify products such as acids, vitamins, antibiotics, or proteins.Cell HarvestingFor example, for intracellular protein-based products, the first step is harvesting the cells. This is typically achieved using centrifugation or filtration to separate the cells from the liquid phase.Cell Disruption for Intracellular ProductsIf the target product is intracellular, the harvested cells must be...
01:17Pulse amplitude and quality
Pulse amplitude is a crucial indicator of cardiac health because it provides valuable insights into the strength of left ventricular contractions and the overall uniformity of blood circulation within the vasculature. The strength of the pulse is directly related to the force with which the heart contracts and the volume of blood being pumped.
A weak or absent pulse may indicate reduced cardiac output or poor left ventricular contraction, which can be signs of cardiovascular dysfunction or...
A weak or absent pulse may indicate reduced cardiac output or poor left ventricular contraction, which can be signs of cardiovascular dysfunction or...
01:10Reconstruction of Signal using Interpolation
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...