Applying Complex-Valued Neural Networks to Acoustic Modeling for Speech Recognition.
Daichi HayakawaTakashi MasukoHiroshi FujimuraPublished in: APSIPA (2018)
Keyphrases
- speech recognition
- complex valued
- neural network
- speech recognition systems
- pattern recognition
- recurrent neural networks
- activation function
- speaker independent
- speech recognizers
- real valued
- speech synthesis
- hidden markov models
- language model
- speech recognizer
- automatic speech recognition
- speech recognition technology
- acoustic models
- speech signal
- back propagation
- feed forward
- noisy environments
- noisy speech
- speaker identification
- linear equations
- genetic algorithm
- multi valued
- blind source separation
- artificial neural networks
- hidden layer
- mel frequency cepstral coefficients
- neural network model
- multi layer perceptron
- speaker recognition
- fuzzy logic
- speaker diarization
- image processing
- speech retrieval
- radial basis function
- document retrieval
- machine learning