A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition.
Albert ZeyerPatrick DoetschPaul VoigtlaenderRalf SchlüterHermann NeyPublished in: ICASSP (2017)
Keyphrases
- speech recognition
- recurrent neural networks
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- automatic speech recognition
- pattern recognition
- acoustic models
- speech synthesis
- language model
- speech understanding
- long short term memory
- speech recognizer
- speech signal
- speech recognition technology
- keyword spotting
- noisy speech
- speech processing
- speech recognition errors
- noisy environments
- artificial neural networks
- speaker identification
- audio visual speech recognition
- neural network
- feed forward
- feature extraction