arXiv (Cornell University) · 2019 · 10 citations · 12 references
ComputingComputer ScienceFeature EngineeringMachine LearningNatural Language ProcessingElectroencephalogram AnalysisElectroencephalogram Signal ProcessingElectroencephalographyNeural NetworksPattern RecognitionSpeech RecognitionAutomatic RecognitionConnectionist Temporal ClassificationEeg Feature ExtractionElectroencephalogram ClassificationElectroencephalography Feature ExtractionLanguage Model PretrainingMachine Learning For ElectroencephalogramTemporal Classification
In this paper we introduce various techniques to improve the performance of electroencephalography (EEG) features based continuous speech recognition (CSR) systems. A connectionist temporal classification (CTC) based automatic speech recognition (ASR) system was implemented for performing recognition. We introduce 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 and we make use of an external language model to improve the beam search during decoding time. We finally study the problem of predicting articulatory features from EEG features in this paper.
12
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Jun‐Young Chung, Çağlar Gülçehre, Kyunghyun Cho et al. · arXiv (Cornell University) · 2014 · 10.8K citations · Full text
Connectionist temporal classification
Alex Graves, Santiago Fernández, Faustino Gomez et al. · 2006 · 5.4K citations