output
20182025
most citedFlauBERT: Unsupervised Language Model Pre-training for French

61 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing cs.SDShow all

1 paper · 1 filter

cs.SD2025

Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting

Guillaume Wisniewski, Séverine Guillaume, Clara Rosina Fernández

Pretrained speech representations like wav2vec2 and HuBERT exhibit strong anisotropy, leading to high similarity between random embeddings. While widely observed, the impact of thi…