2 papers
cs.SD2020
Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers
Zeqian Li, Jacob Whitehill
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedd…
cs.LG2020
Compositional Embeddings for Multi-Label One-Shot Learning
Zeqian Li, Michael C. Mozer, Jacob Whitehill
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we prop…