迈向对话式匈牙利语语音识别：介绍BEA-Large和BEA-Dialogue数据集
Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
AI总结：
本文介绍了BEA-Large和BEA-Dialogue两个匈牙利语语音数据集，用于提升对话式语音识别技术，并展示了基于这些数据集的ASR模型性能及说话人识别结果。
摘要：
自动语音识别（ASR）的进步在很大程度上得益于高资源语言中的大量数据集，而像匈牙利语这样的语言由于缺乏自发性和对话性语料库而处于代表性不足的状态。为了解决这一差距，我们引入了两个新的数据集——BEA-Large和BEA-Dialogue——这些数据集是从之前未处理的匈牙利语语音语料库BEA中构建的。BEA-Large通过增加433名说话者255小时的自发语音，扩展了BEA-Base，并附有详细的段级元数据。BEA-Dialogue包含85小时的自发对话，是一个匈牙利语语音语料库，其对话被划分为不依赖说话者的子集，支持对话式ASR和说话人识别的研究。我们利用公开可用的ASR模型在这些数据集上建立了可重复的基线，经过微调的Fast Conformer模型在自发语音上的词错误率低至14.18%，在重复语音上的词错误率低至4.8%。识别实验的识别错误率在12.46%到17.40%之间，为未来改进提供了参考点。结果突显了对话式ASR的持续困难，特别是由于不流畅、重叠和非正式语音模式。通过发布这些数据集和基线，我们旨在推进匈牙利语音技术，并为其他语言的自发性和对话性基准开发提供方法论框架。
英文摘要：
The advancement of automatic speech recognition (ASR) has been largely enhanced by extensive datasets in high-resource languages, while languages such as Hungarian remain underrepresented due to limited spontaneous and conversational corpora. To address this gap, we introduce two new datasets -- BEA-Large and BEA-Dialogue -- constructed from the previously unprocessed portions of the Hungarian speech corpus named BEA. BEA-Large extends BEA-Base with 255 hours of spontaneous speech from 433 speakers, enriched with detailed segment-level metadata. BEA-Dialogue, comprising 85 hours of spontaneous conversations, is a Hungarian speech corpus featuring natural dialogues partitioned into speaker-independent subsets, supporting research in conversational ASR and speaker diarization. We establish reproducible baselines on these datasets using publicly available ASR models, with the fine-tuned Fast Conformer model achieving word error rates as low as 14.18% on spontaneous and 4.8% on repeated speech. Diarization experiments yield diarization error rates between 12.46% and 17.40%, providing reference points for future improvements. The results highlight the persistent difficulty of conversational ASR, particularly due to disfluencies, overlaps, and informal speech patterns. By releasing these datasets and baselines, we aim to advance Hungarian speech technology and offer a methodological framework for developing spontaneous and conversational benchmarks in other languages.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
