I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription.
Vishwa GuptaPatrick KennyPierre OuelletThemos StafylakisPublished in: ICASSP (2014)
Keyphrases
- neural network
- speaker adaptation
- automatic transcription
- speaker dependent
- speech recognition
- speaker identification
- automatic speech recognition
- multimedia
- feature vectors
- pattern recognition
- visual information
- visual data
- audio visual
- hidden markov models
- speech recognition systems
- gaussian mixture model
- deep learning
- acoustic features
- spontaneous speech
- speaker independent