用监督学习提升语音分词精度，效果超越现有方法。
Back to Supervision: Boosting Word Boundary Detection through Frame Classification
- 采用标签增强与帧选择策略，实现模型无关的监督分词
- 在Buckeye和TIMIT数据集上分别达到0.8427和0.7436的F值
- 适用于需要高质量音频切分的语音研究与下游任务
语音分词在词级和音素级对多种语音处理任务至关重要，有助于从语句中提取有意义的单元，从而生成离散元素。本文提出一种模型无关的监督式词边界检测框架，结合标签增强技术和输出帧选择策略。在Buckeye数据集上进行训练与测试，并在TIMIT数据集上仅做测试，使用了包括预训练模型（Wav2Vec 2.0、HuBERT）以及卷积和卷积循环网络在内的先进编码器。采用HuBERT编码器的方法在相同数据集上超越了其他最先进的架构，无论其是否为监督或自监督训练。具体而言，在Buckeye数据集上取得0.8427的F值和0.8489的R值，在TIMIT数据集上分别为0.7436和0.7807。这些结果在两个数据集上均创下新纪录。该方法不仅解决了当前任务，还为未来音频标记化研究提供了稳健高效的预处理方案。
原文摘要 · Abstract (English)
Speech segmentation at both word and phoneme levels is crucial for various speech processing tasks. It significantly aids in extracting meaningful units from an utterance, thus enabling the generation of discrete elements. In this work we propose a model-agnostic framework to perform word boundary detection in a supervised manner also employing a labels augmentation technique and an output-frame selection strategy. We trained and tested on the Buckeye dataset and only tested on TIMIT one, using state-of-the-art encoder models, including pre-trained solutions (Wav2Vec 2.0 and HuBERT), as well as convolutional and convolutional recurrent networks. Our method, with the HuBERT encoder, surpasses the performance of other state-of-the-art architectures, whether trained in supervised or self-supervised settings on the same datasets. Specifically, we achieved F-values of 0.8427 on the Buckeye dataset and 0.7436 on the TIMIT dataset, along with R-values of 0.8489 and 0.7807, respectively. These results establish a new state-of-the-art for both datasets. Beyond the immediate task, our approach offers a robust and efficient preprocessing method for future research in audio tokenization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。