OpenFEAT: Improving Speaker Identification by Open-Set Few-Shot Embedding Adaptation with Transformer

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 op...

Full description

Saved in:
Bibliographic Details
Main Authors: Kishan, K C, Tan, Zhenning, Chen, Long, Jin, Minho, Han, Eunjung, Stolcke, Andreas, Lee, Chul
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
embedding adaptation
Error analysis
few-shot open-set learning
Signal processing
Signal processing algorithms
speaker identification
Training
Transformers
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747613