English

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

Audio and Speech Processing 2024-02-09 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2202.12349,
  title  = {openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer},
  author = {Kishan K C and Zhenning Tan and Long Chen and Minho Jin and Eunjung Han and Andreas Stolcke and Chul Lee},
  journal= {arXiv preprint arXiv:2202.12349},
  year   = {2024}
}

Comments

To appear in Proc. IEEE ICASSP 2022

R2 v1 2026-06-24T09:53:00.613Z