On relevant BBC Rewind queries, a zero-shot pipeline of PyAnnote diarisation plus ECAPA or TitaNet embeddings reaches about 86 to 87% P@1 and tolerates many distortions.
On the usefulness of speaker embeddings for speaker retrieval in the wild: A comparative study of x-vector and ecapa-tdnn models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness
On relevant BBC Rewind queries, a zero-shot pipeline of PyAnnote diarisation plus ECAPA or TitaNet embeddings reaches about 86 to 87% P@1 and tolerates many distortions.