Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification.
Yingke ZhuTom KoDavid SnyderBrian MakDaniel PoveyPublished in: INTERSPEECH (2018)
Keyphrases
- speaker verification
- speaker recognition
- noisy environments
- language identification
- prosodic features
- audio visual
- text mining
- text to speech
- acoustic features
- multilayer perceptron
- emotion recognition
- using artificial neural networks
- information retrieval
- face verification
- gaussian mixture model
- speech recognition
- high dimensional data
- keywords
- image processing