Classifying Unprompted Speech by Retraining LSTM Nets.
Nicole BeringerAlex GravesFlorian SchielJürgen SchmidhuberPublished in: ICANN (1) (2005)
Keyphrases
- speech recognition
- speech signal
- audio visual
- endpoint detection
- recognition engine
- speaker identification
- text to speech
- recurrent neural networks
- speech processing
- speech synthesis
- speaker recognition
- language acquisition
- audio stream
- information retrieval
- hierarchical classification
- linear prediction
- machine learning
- speaker diarization
- pattern recognition
- automatically classify