• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.161-168
• /
• 2021

In this paper, a Silent Speech Interface (SSI) technology was proposed in which Doppler frequency shifts of the reflected signal were used to synthesize the speech signals when 40kHz ultrasonic signal was incident to speaker's mouth region. In SSI, the mapping rules from the features derived from non-speech signals to those from audible speech signals was constructed, the speech signals are synthesized from non-speech signals using the constructed mapping rules. The mapping rules were built by minimizing the overall errors between the estimated and true speech parameters in the conventional SSI methods. In the present study, the mapping rules were constructed so that the distribution of the estimated parameters is similar to that of the true parameters by using Generative Adversarial Networks (GAN). The experimental result using 60 Korean words showed that, both objectively and subjectively, the performance of the proposed method was superior to that of the conventional neural networks-based methods.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.3
• /
• pp.140-147
• /
• 2024

This paper explores the recent advancements in speech recognition technology, focusing on the integration of artificial intelligence to improve recognition accuracy in challenging environments, such as noisy or low-quality audio conditions. Traditional speech recognition methods often suffer from performance degradation in noisy settings. However, the application of deep neural networks (DNN) has led to significant improvements, enabling more robust and reliable recognition in various industries, including banking, automotive, healthcare, and manufacturing. A key area of advancement is the use of Silent Speech Interfaces (SSI), which allow communication through non-speech signals, such as visual cues or other auxiliary signals like ultrasound and electromyography, making them particularly useful for individuals with speech impairments. The paper further discusses the development of multi-modal speech recognition, combining both audio and visual inputs, which enhances recognition accuracy in noisy environments. Recent research into lip-reading technology and the use of deep learning architectures, such as CNN and RNN, has significantly improved speech recognition by extracting meaningful features from video signals, even in difficult lighting conditions. Additionally, the paper covers the use of self-supervised learning techniques, like AV-HuBERT, which leverage large-scale, unlabeled audiovisual datasets to improve performance. The future of speech recognition technology is likely to see further integration of AI-driven methods, making it more applicable across diverse industries and for individuals with communication challenges. The conclusion emphasizes the need for further research, especially in languages with complex morphological structures, such as Korean

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.90-95
• /
• 2014

The researchs using brain-computer interface, the new interface system which connect human to macine, have been maded to implement the user-assistance devices for control of wheelchairs or input the characters. In recent researches, there are several trials to implement the speech recognitions system based on the brain wave and attempt to silent communication. In this paper, we studied how to extract features of vowel based on international phonetic alphabet (IPA), as a foundation step for implementing of speech recognition system based on electroencephalogram (EEG). We conducted the 2 step experiments with three healthy male subjects, and first step was speaking imagery with single vowel and second step was imagery with successive two vowels. We selected 32 channels, which include frontal lobe related to thinking and temporal lobe related to speech function, among acquired 64 channels. Eigen value of the signal was used for feature vector and support vector machine (SVM) was used for classification. As a result of first step, we should use over than 10th order of feature vector to analyze the EEG signal of speech and if we used 11th order feature vector, the highest average classification rate was 95.63 % in classification between /a/ and /o/, the lowest average classification rate was 86.85 % with /a/ and /u/. In the second step of the experiments, we studied the difference of speech imaginary signals between single and successive two vowels.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.1
• /
• pp.74-82
• /
• 2016

In this paper, a new automatic speech recognition (ASR) was proposed where ultrasonic doppler signals were used, instead of conventional speech signals. The proposed method has the advantages over the conventional speech/non-speech-based ASR including robustness against acoustic noises and user comfortability associated with usage of the non-contact sensor. In the method proposed herein, 40 kHz ultrasonic signal was radiated toward to the mouth and the reflected ultrasonic signals were then received. Frequency shift caused by the doppler effects was used to implement ASR. The proposed method employed multi-channel ultrasonic signals acquired from the various locations, which is different from the previous method where single channel ultrasonic signal was employed. The PCA(Principal Component Analysis) coefficients were used as the features of ASR in which hidden markov model (HMM) with left-right model was adopted. To verify the feasibility of the proposed ASR, the speech recognition experiment was carried out the 60 Korean isolated words obtained from the six speakers. Moreover, the experiment results showed that the overall word recognition rates were comparable with the conventional speech-based ASR methods and the performance of the proposed method was superior to the conventional signal channel ASR method. Especially, the average recognition rate of 90 % was maintained under the noise environments.