paper_authors: Dejan Porjazovski, Tamás Grósz, Mikko Kurimo
for: 这篇论文旨在检验非标准的话语识别方案，以寻找不需要自动话语识别系统（ASR）的解决方案。
methods: 这篇论文使用了音频只和多模态组合方法来识别非标准的芬兰语。
results: 研究发现，听音只的方法在ASR系统不可用时是一个可行的选择，而多模态组合方法在识别性能上表现最佳。Abstract
Traditional topic identification solutions from audio rely on an automatic speech recognition system (ASR) to produce transcripts used as input to a text-based model. These approaches work well in high-resource scenarios, where there are sufficient data to train both components of the pipeline. However, in low-resource situations, the ASR system, even if available, produces low-quality transcripts, leading to a bad text-based classifier. Moreover, spontaneous speech containing hesitations can further degrade the performance of the ASR model. In this paper, we investigate alternatives to the standard text-only solutions by comparing audio-only and hybrid techniques of jointly utilising text and audio features. The models evaluated on spontaneous Finnish speech demonstrate that purely audio-based solutions are a viable option when ASR components are not available, while the hybrid multi-modal solutions achieve the best results.
摘要
传统的话题识别解决方案从音频中获得的听写系统（ASR）生成的讲解作为输入，用文本基于模型进行识别。这些方法在高资源场景下工作良好，因为可以在训练两个组件的气候下进行训练。然而，在低资源情况下，即使有ASR系统，也会生成低质量的讲解，导致文本基于模型的性能下降。此外，不慎的语音中的停顿也可能使ASR模型的性能下降。在这篇论文中，我们调查了标准文本仅解决方案的代替方案，比较音频仅、多模态融合等方法的性能。我们在自然的芬兰语音中评估了这些模型，得到的结论是：当ASR组件不可用时，听写仅的解决方案是一个可靠的选择；而多模态融合解决方案在性能上表现最佳。
MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems
results: 这个论文的结果表明，基于时间约束的cpWER计算方法可以提高匹配质量，同时也可以提高匹配速度。此外，这个方法还可以使用不准确的时间标签来进行匹配，从而降低了计算成本。Abstract
MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription systems. It provides a unified interface for the computation of commonly used Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other WER definitions. We extend the cpWER computation by a temporal constraint to ensure that only words are identified as correct when the temporal alignment is plausible. This leads to a better quality of the matching of the hypothesis string to the reference string that more closely resembles the actual transcription quality, and a system is penalized if it provides poor time annotations. Since word-level timing information is often not available, we present a way to approximate exact word-level timings from segment-level timings (e.g., a sentence) and show that the approximation leads to a similar WER as a matching with exact word-level annotations. At the same time, the time constraint leads to a speedup of the matching algorithm, which outweighs the additional overhead caused by processing the time stamps.
摘要
美特评估是一个开源工具kit，用于评估各种会议笔记系统。它提供一个统一的接口来计算常用的单词错误率（WER），包括cpWER、ORC WER 和 MIMO WER 等 WER 定义。我们在cpWER 计算中添加了时间约束，以确保只有在时间对齐是可能的时候才认为单词是正确的。这会导致匹配假设字符串与参考字符串的匹配更加精准，系统会受到负面抑制，如果它提供了低质量的时间标记。由于单词水平的时间信息通常不可用，我们提出了一种将 sentence 级别的时间信息约化为单词级别的时间信息的方法，并证明这种约化导致与匹配精度相似的 WER。同时，时间约束会使匹配算法加速，这些加速的效果超过了对处理时间戳的额外开销。