Speech Recognition with No Speech or with Noisy Speech

@article{Krishna2019SpeechRW,
  title={Speech Recognition with No Speech or with Noisy Speech},
  author={Gautam Krishna and Co Tran and Jianguo Yu and Ahmed H. Tewfik},
  journal={ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2019},
  pages={1090-1094}
}
  • G. Krishna, Co Tran, +1 author A. Tewfik
  • Published 2019
  • Computer Science, Mathematics, Engineering
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. [...] Key Result Finally, we demonstrate the ability to recognize words from EEG with no speech signal on a limited English vocabulary with high accuracy.Expand
Advancing Speech Recognition With No Speech Or With Noisy Speech
TLDR
End to end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input is demonstrated and CSR for noisy speech is demonstrated by fusing with EEG features. Expand
Continuous Speech Recognition using EEG and Video
TLDR
This paper implemented a connectionist temporal classification based end-to-end automatic speech recognition (ASR) model for performing recognition and demonstrates that EEG features are helpful in enhancing the performance of continuous visual speech recognition systems. Expand
Continuous Silent Speech Recognition using EEG
TLDR
A connectionist temporal classification (CTC) automatic speech recognition model was implemented to translate EEG signals recorded in parallel while subjects were reading English sentences in their mind without producing any voice to text. Expand
Understanding effect of speech perception in EEG based speech recognition systems
TLDR
Both isolated and continuous speech recognition using EEG signals recorded in parallel with listening, speaking are demonstrated and the previous connectionist temporal classification (CTC) model results demonstrated by authors in [1] are improved. Expand
An ensemble technique for speech recognition in noisy environments
TLDR
This research proposed an ensemble technique that does not rely on a single filter for perfect noise reduction but incorporates information from multiple noise reduction filters to improve the final ASR accuracy. Expand
Voice Activity Detection in presence of background noise using EEG
TLDR
Performance of voice activity detection system operating in presence of background noise can be improved by concatenating acoustic input features with electroencephalography (EEG) features by implementing a recurrent neural network (RNN) based VAD system. Expand
State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG
TLDR
The results demonstrate the feasibility of using EEG signals for continuous noisy speech recognition under different experimental conditions and the preliminary results for synthesis of speech from EEG features are provided. Expand
Improving EEG based Continuous Speech Recognition
TLDR
The problem of predicting articulatory features from EEG features in this paper is studied and techniques to initialize the weights of the recurrent layers in the encoder of the CTC model with more meaningful weights rather than with random weights are introduced. Expand
EEG based Continuous Speech Recognition using Transformers
TLDR
The results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (RNN) based sequence-to-sequence EEG models and better performance during inference time for smaller test set vocabulary but as the vocabulary size increases, the performance of the RNN based models were better than transformer based models on a limited English vocabulary. Expand
Speech Recognition using EEG signals recorded using dry electrodes
TLDR
Speech recognition using electroencephalography (EEG) signals obtained using dry electrodes on a limited English vocabulary consisting of three vowels and one word using a deep learning model is demonstrated. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 46 REFERENCES
Advancing Speech Recognition With No Speech Or With Noisy Speech
TLDR
End to end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input is demonstrated and CSR for noisy speech is demonstrated by fusing with EEG features. Expand
State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG
TLDR
The results demonstrate the feasibility of using EEG signals for continuous noisy speech recognition under different experimental conditions and the preliminary results for synthesis of speech from EEG features are provided. Expand
Voice command recognition using EEG signals
TLDR
Automatic speech recognition of spoken words from brain waves based on digital signal processing and machine learning methods is proposed to bring better understanding of speech production. Expand
Combining acoustic and articulatory feature information for robust speech recognition
TLDR
It is shown that articulatory feature (AF) systems are capable of achieving a superior performance at high noise levels and that the combination of acoustic and AFs consistently leads to a significant reduction of word error rate across all acoustic conditions. Expand
Multilingual Speech Recognition
The speech-to-speech translation system Verbmobil requires a multilingual setting. This consists of recognition engines in the three languages German, English and Japanese that run in one commonExpand
Speech processing with a cortical representation of audio
  • N. Mesgarani, S. Shamma
  • Computer Science
  • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2011
TLDR
A computational cortical model is used to illustrate how phonetic features appear in such a multiresolution representation of phonemic acoustic features and how this representation has been successfully applied in variety of speech processing tasks including robust speech discrimination, speech enhancement and phoneme recognition. Expand
Brain-computer interface technology for speech recognition: A review
TLDR
An overview of the studies that have been conducted with the purpose of understanding the use of brain signals as input to a speech recogniser with a summary of the methodologies used and achieved results. Expand
Envisioned speech recognition using EEG sensors
TLDR
A coarse-to-fine-level envisioned speech recognition framework with the help of EEG signals that outperforms the existing research work in terms of accuracy and robustness is proposed. Expand
Towards End-To-End Speech Recognition with Recurrent Neural Networks
This paper presents a speech recognition system that directly transcribes audio data with text, without requiring an intermediate phonetic representation. The system is based on a combination of theExpand
Robust Sound Event Classification Using Deep Neural Networks
TLDR
A sound event classification framework is outlined that compares auditory image front end features with spectrogram image-based frontEnd features, using support vector machine and deep neural network classifiers, and is shown to compare very well with current state-of-the-art classification techniques. Expand
...
1
2
3
4
5
...