Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling.
Jürgen T. GeigerZixing ZhangFelix WeningerBjörn W. SchullerGerhard RigollPublished in: INTERSPEECH (2014)
Keyphrases
- recurrent neural networks
- long short term memory
- nonlinear dynamic systems
- neural network
- feed forward
- reservoir computing
- recurrent networks
- complex valued
- echo state networks
- artificial neural networks
- cascade correlation
- noisy environments
- feedforward neural networks
- speech recognition
- neural model
- acoustic features
- decision making
- audio visual
- speech recognition systems
- artificial intelligence
- machine learning