Czech is a very specific language due to its large differences between the
formal and the colloquial form of speech. While the formal (written) form is
used mainly in official documents, literature, and public speeches, the
colloquial (spoken) form is used widely among people in casual speeches. This
gap introduces serious problems for ASR systems, especially when training or
evaluating ASR models on datasets containing a lot of colloquial speech, such
as the MALACH project. In this paper, we are addressing this problem in the
light of a new paradigm in end-to-end ASR systems -- recently introduced
self-supervised audio Transformers. Specifically, we are investigating the
influence of colloquial speech on the performance of Wav2Vec 2.0 models and
their ability to transcribe colloquial speech directly into formal transcripts.
We are presenting results with both formal and colloquial forms in the training
transcripts, language models, and evaluation transcripts.

本文研究以最新的端到端自监督音频 Transformer 技术为基础，探讨非正式口语形式对 Wav2Vec 2.0 模型性能和转录正式文本的影响，并提出具有正式和非正式语言模型的训练方案及评测结果。

MALACH 项目中基于 Transformer 的正式与口语捷克语自动语音识别

Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project

Self-supervised Audio Transformers (SAT) enable great success in many
downstream speech applications like ASR, but how they work has not been widely
explored yet. In this work, we present multiple strategies for the analysis of
attention mechanisms in SAT. We categorize attentions into explainable
categories, where we discover each category possesses its own unique
functionality. We provide a visualization tool for understanding multi-head
self-attention, importance ranking strategies for identifying critical
attention, and attention refinement techniques to improve model performance.

本文介绍了多种针对 Self-supervised Audio Transformers 中注意力机制分析的策略，包括解释每种类型的注意力机制的功能、提供可视化工具以了解多头自注意力、重要性排名策略以识别关键注意力，以及注意力精炼技术以提高模型性能。