On deep speaker embeddings for text-independent speaker recognition.
Sergey NovoselovAndrey ShulipaIvan KremnevAlexandr KozlovVadim ShchemelininPublished in: Odyssey (2018)
Keyphrases
- object recognition
- recognition rate
- activity recognition
- automatic recognition
- recognition accuracy
- feature extraction
- pattern recognition
- visual recognition
- character recognition
- recognition algorithm
- speaker verification
- shape recognition
- automatic speech recognition
- image recognition
- euclidean space
- human activities
- low dimensional
- dimensionality reduction
- hand gestures
- audio visual
- neural network
- similarity measure
- automatic transcription