In this paper, we present a transcribed corpus of the LIBE committee of the
EU parliament, totalling 3.6 Million running words. The meetings of
parliamentary committees of the EU are a potentially valuable source of
information for political scientists but the data is not readily available
because only disclosed as speech recordings together with limited metadata. The
meetings are in English, partly spoken by non-native speakers, and partly
spoken by interpreters. We investigated the most appropriate Automatic Speech
Recognition (ASR) model to create an accurate text transcription of the audio
recordings of the meetings in order to make their content available for
research and analysis. We focused on the unsupervised domain adaptation of the
ASR pipeline. Building on the transformer-based Wav2vec2.0 model, we
experimented with multiple acoustic models, language models and the addition of
domain-specific terms. We found that a domain-specific acoustic model and a
domain-specific language model give substantial improvements to the ASR output,
reducing the word error rate (WER) from 28.22 to 17.95. The use of
domain-specific terms in the decoding stage did not have a positive effect on
the quality of the ASR in terms of WER. Initial topic modelling results
indicated that the corpus is useful for downstream analysis tasks. We release
the resulting corpus and our analysis pipeline for future research.

本文提出了一个欧盟议会 LIBE 委员会的书面语料库，总计 3.6 百万字。在实验过程中，我们使用基于 transformer 的 Wav2vec2.0 模型作为自动语音识别（ASR）流程的基础，并尝试了多个音频模型，语言模型和特定领域术语的添加来适应领域。结果表明，特定领域的音频模型和语言模型显着提高了 ASR 输出的质量，将错误率从 28.22 降至 17.95，并对下游分析任务有用。