S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder.
Narla John Metilda Sagaya MarySrinivasan UmeshSandesh Varadaraju KattaPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2022)
Keyphrases
- speaker verification
- speech recognition
- speaker recognition
- vector space
- audio visual
- speaker diarization
- fuzzy logic
- speaker identification
- low complexity
- automatic speech recognition
- dimensionality reduction
- maximum likelihood
- multi modal
- motion estimation
- pattern recognition
- video codec
- face recognition
- neural network
- data sets