Sorry, you need to enable JavaScript to visit this website.

OPENFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer

Citation Author(s):
Kishan K C, Zhenning Tan, Long Chen, Minho Jin, Eunjung Han, Andreas Stolcke, Chul Lee
Submitted by:
Kishan KC
Last updated:
9 May 2022 - 11:36am
Document Type:
Poster
Document Year:
2022
Event:
Presenters:
Kishan K C
Paper Code:
SPE-37.2
 

Household speaker identification with few enrollment utterances is an important yet challenging problem, especially when household members share similar voice characteristics and room acoustics. A common embedding space learned from a large number of speakers is not universally applicable for the optimal identification of every speaker in a household. In this work, we first formulate household speaker identification as a few-shot open-set recognition task and then propose a novel embedding adaptation framework to adapt speaker representations from the given universal embedding space to a household-specific embedding space using a set-to-set function, yielding better household speaker identification performance. With our algorithm, Open-set Few-shot Embedding Adaptation with Transformer (openFEAT), we observe that the speaker identification equal error rate (IEER) on simulated households with 2 to 7 hard-to-discriminate speakers is reduced by 23% to 31% relative.

up
0 users have voted: