Self-Supervised Speaker Embeddings.
Themos StafylakisJohan RohdinOldrich PlchotPetr MizeraLukás BurgetPublished in: INTERSPEECH (2019)
Keyphrases
- vector space
- speaker verification
- speech recognition
- speaker recognition
- low dimensional
- dimensionality reduction
- manifold learning
- automatic speech recognition
- audio visual
- speaker diarization
- machine learning
- website
- distance measure
- multi modal
- euclidean space
- high dimensional data
- database
- image retrieval
- decision trees
- genetic algorithm
- real world