LISE decomposes pretrained speaker embeddings into components that preserve ASV performance with negligible EER degradation and enable listeners to distinguish speakers at 83.9% accuracy.
Leveraging speaker attribute information using multi task learning for speaker verification and diarization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LISE : Listenable Interpretable Speaker Embeddings
LISE decomposes pretrained speaker embeddings into components that preserve ASV performance with negligible EER degradation and enable listeners to distinguish speakers at 83.9% accuracy.