paper-with-me

Papers

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

2025-06-06 · 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 this property on downstream tasks remains unclear. This work evaluates anisotropy in keyword spotting for computational documentary linguistics. Using Dynamic Time Warping, we show that despite anisotropy, wav2vec2 similarity measures effectively identify words without transcription. Our results highlight the robustness of these representations, which capture phonetic structures and generalize across speakers. Our results underscore the importance of pretraining in learning rich and invariant speech representations.

📄 PDF Abstract BibTeX arXiv:2506.11096

Code (0)

등록된 구현이 없습니다.

Tasks

Dynamic Time WarpingKeyword Spotting

Similar Papers 제목 키워드 기반

Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing

2024-10-15 · Richard Diehl Martinez, Zebulon Goriely, Andrew Caines, Paula Buttery 외

Language models strongly rely on frequency information because they maximize the likelihood of tokens during pre-training. As a consequence, language models tend to not generalize well to tokens that are seldom seen duri…

Language ModelingLanguage ModellingSentence

Is there Anisotropy in Structural Bias?

2021-05-10 · Diederick Vermetten, Anna V. Kononova, Fabio Caraffini, Hao Wang 외

Structural Bias (SB) is an important type of algorithmic deficiency within iterative optimisation heuristics. However, methods for detecting structural bias have not yet fully matured, and recent studies have uncovered m…

Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models

2024-06-07 · Malo Maisonneuve, Corinne Fredouille, Muriel Lalain, Alain Ghio 외

Head and Neck Cancers (HNC) significantly impact patients' ability to speak, affecting their quality of life. Commonly used metrics for assessing pathological speech are subjective, prompting the need for automated and u…

Anisotropy Is Inherent to Self-Attention in Transformers

2024-01-22 · Nathan Godey, Éric de la Clergerie, Benoît Sagot

The representation degeneration problem is a phenomenon that is widely observed among self-supervised learning methods based on Transformers. In NLP, it takes the form of anisotropy, a singular property of hidden represe…

Self-Supervised Learning

Is Anisotropy Inherent to Transformers?

2023-06-13 · Nathan Godey, Éric de la Clergerie, Benoît Sagot

The representation degeneration problem is a phenomenon that is widely observed among self-supervised learning methods based on Transformers. In NLP, it takes the form of anisotropy, a singular property of hidden represe…

Self-Supervised Learning