Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review

@article{Lee2021BiosignalSA,
  title={Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review},
  author={Wookey Lee and Jessica Jiwon Seong and Busra Ozlu and Bong Sup Shim and Azizbek Marakhimov and Suan Lee},
  journal={Sensors (Basel, Switzerland)},
  year={2021},
  volume={21}
}
Voice is one of the essential mechanisms for communicating and expressing one’s intentions as a human being. There are several causes of voice inability, including disease, accident, vocal abuse, medical surgery, ageing, and environmental pollution, and the risk of voice loss continues to increase. Novel approaches should have been developed for speech recognition and production because that would seriously undermine the quality of life and sometimes leads to isolation from society. In this… 

Recognition of EEG Signals from Imagined Vowels Using Deep Learning Methods

A new algorithm based on Deep Learning (DL) to recognize EEG signals in imagined vowel tasks, referred to as CNNeeg1-1, is developed and the results show that for intra-subject training analysis, the best performance among the Shallow CNN, EEGNet, and CNNEEg 1-1 methods in classifying imagined vowels was exhibited.

Harris Hawks Sparse Auto-Encoder Networks for Automatic Speech Recognition System

This paper uses speech information from jim-schwoebel voice datasets processed by Mel-frequency cepstral coefficients (MFCCs) to recognize speech, and uses a sparse auto-encoder (SAE) neural network and the hidden Markov model (HMM) to decide on the speech recognition.

Brain Computer Interface -EEG Based Imagined Word Prediction Using Convolutional Neural Network Visual Stimuli for Speech Disability

The Alexnet transfer learning model is selected to be the best model as compared Googlenet, as it achieved an accuracy of 90.3% and the final training option of 80 epoch, 64 batch size, scalogram pre-processing method, ratio of 80:20 training and validation set and initial learning rate of 0.0001.

Steering a Robotic Wheelchair Based on Voice Recognition System Using Convolutional Neural Networks

A low-cost software and hardware method to steer a robotic wheelchair using a convolutional neural network (CNN)-based network-in-network (NIN) structure approach integrated with a voice recognition model was designed and implemented.

Tongue Contour Tracking and Segmentation in Lingual Ultrasound for Speech Recognition: A Review

A comparative analysis and review based on quantitative and qualitative criteria of the two main streams of tongue contour segmentation from ultrasound images shows that tongue tracking using machine learning-based techniques is superior to traditional techniques, considering the performance and algorithm generalization ability.

Toward Smart Communication Components: Recent Advances in Human and AI Speaker Interaction

This study aims to investigate how humans and artificial intelligence (AI) speakers interact and to examine the interactions based on three types of communication failures: system, semantic, and

A Study on Deriving Improvements through User Recognition Analysis of Artificial Intelligence Speakers

It is concluded that artificial intelligence is similar to an automated machine that simply finds the data among many data connected to the Internet, plays music, and connects to a site where you can shop and process it non-face-to-face.

Measuring Biosignals with Single Circuit Boards

This review gives an overview of studies found in the recent scientific literature, reporting measurements of biosignals such as ECG, EMG, sweat and other health-related parameters by single circuit boards, showing new possibilities offered by Arduino, Raspberry Pi etc. in the mobile long-term acquisition of biosignedals.

Real-Time Object Tracking Algorithm Based on Siamese Network

An innovative feature pyramid and optical flow estimation based on the Siamese network for object tracking, which is called SiamFP, which obtains state-of-the-art performance on OTB50, OTB2015, and VOT2016 benchmarks while exhibiting better real-time and robustness.

Using AAEHS-Net as an Attention-Based Auxiliary Extraction and Hybrid Subsampled Network for Semantic Segmentation

A semantic segmentation network-attention-based auxiliary extraction and hybrid subsampled network (AAEHS-Net) is suggested in this study and has obtained the best values for all evaluation metrics in three datasets compared to the currently popular algorithms.

References

SHOWING 1-10 OF 120 REFERENCES

Development of sEMG sensors and algorithms for silent speech recognition

A new system of face- and neck-worn sensors and signal processing algorithms that are capable of recognizing silently mouthed words and phrases entirely from the surface electromyographic (sEMG) signals recorded from muscles of the face and neck that are involved in the production of speech are developed.

Biosignal-Based Spoken Communication: A Survey

An overview of the various modalities, research approaches, and objectives for biosignal-based spoken communication is given.

Silent Speech Interfaces for Speech Restoration: A Review

A number of challenges remain to be addressed in future research before SSIs can be promoted to real-world applications, and future SSIs will improve the lives of persons with severe speech impairments by restoring their communication capabilities.

Silent speech recognition from articulatory movements using deep neural network

Deep neural network (DNN)-hidden Markov model (HMM) is investigated in recognizing speech from articulatory movement data and results indicated the performance improvement of DNN-HMM over GMMHMM over Gaussian mixture model (GMM)-HMM in silent speech recognition.

SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks

A system to detect a user's unvoiced utterance and recognize the utterance contents without the user's uttering voice is proposed, and it is confirmed that audio signals generated by the system can control the existing smart speakers.

Isolated word recognition of silent speech using magnetic implants and sensors.

EMG-to-Speech: Direct Generation of Speech From Facial Electromyographic Signals

  • M. JankeLorenz Diener
  • Computer Science
    IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2017
The characteristics of the speech EMG signal are described, techniques for extracting relevant features are introduced, different EMG-to-speech mapping methods are presented, and an evaluation of the different methods for real-time capability and conversion quality is presented.

Enhancement of EMG-based Thai number words classification using frame-based time domain features with stacking filter

The results show that using above techniques of feature extraction, feature dimensionality reduction and classification can improve an average accuracy rate by 3% absolute for audible speech when were compared to earlier work.

Preliminary Test of a Wireless Magnetic Tongue Tracking System for Silent Speech Interface

A prototype, wireless, permanent magnet articulography (PMA)-based tongue motion tracking system for SSI purpose that converts non-audio information such as articulatory movement to text that can then drive a text-to-speech synthesizer.

Modeling coarticulation in EMG-based continuous speech recognition

...