arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.06174eess.AS
收藏

在低资源语言中进行有效的无ASR关键字识别的特征学习

Feature learning for efficient ASR-free keyword spotting in low-resource languages

Ewald van der Westhuizen, Herman Kamper, Raghav Menon, John Quinn, Thomas Niesler

摘要:

我们认为特征学习可以有效地识别关键字,可以应用于资源严重不足的环境中。目的是支助联合国在非洲几乎没有语文资源的部分地区的人道主义救济方案。为了在这样的语言中快速开发,我们依赖于一个小的、易于编译的独立关键字集。这些关键字模板被应用到一个大的语料库的域中,但未转录的语音使用动态时间规整(DTW)。所得到的DTW对齐分数用于训练卷积神经网络(CNN),其在计算上更有效并且适合于实时应用的数量级。我们通过在这个几乎为零的资源设置中识别鲁棒的声学特征来优化这个神经网络关键字识别器。首先,我们采用多语言瓶颈特征(BNF)提取器将来自资源丰富但不相关的语言的信息合并起来。接下来,我们考虑从在域内但未转录的数据上训练的自动编码器(AE)中提取的特征。最后,我们考虑对应的自动编码器(CAE)功能,这是微调的一小部分,在域标记的数据。在南非英语和卢甘达,一种低资源的语言,实验表明,BNF和CAE功能实现了5%的相对性能提高基线MFCC。然而,使用BNF作为CAE的输入,在ROC曲线下面积(AUC)方面比MFCC有超过27%的相对改善,并且前10名检索的数量是其两倍多。我们表明,使用这些功能,CNN-DTW关键字定位器的表现几乎与DTW关键字定位器一样好,同时优于仅在关键字模板上训练的基线CNN。CNN-DTW关键字定位器使用BNF衍生的CAE功能,代表了一种高效的方法,具有竞争力的性能,适合在资源严重不足的情况下快速部署。

英文摘要:

We consider feature learning for efficient keyword spotting that can be applied in severely under-resourced settings. The objective is to support humanitarian relief programmes by the United Nations in parts of Africa in which almost no language resources are available. For rapid development in such languages, we rely on a small, easily-compiled set of isolated keywords. These keyword templates are applied to a large corpus of in-domain but untranscribed speech using dynamic time warping (DTW). The resulting DTW alignment scores are used to train a convolutional neural network (CNN) which is orders of magnitude more computationally efficient and suitable for real-time application. We optimise this neural network keyword spotter by identifying robust acoustic features in this almost zero-resource setting. First, we incorporate information from well-resourced but unrelated languages using a multilingual bottleneck feature (BNF) extractor. Next, we consider features extracted from an autoencoder (AE) trained on in-domain but untranscribed data. Finally, we consider correspondence autoencoder (CAE) features which are fine-tuned on the small set of in-domain labelled data. Experiments in South African English and Luganda, a low-resource language, show that BNF and CAE features achieve a 5% relative performance improvement over baseline MFCCs. However, using BNFs as input to the CAE results in a more than 27% relative improvement over MFCCs in ROC area-under-the-curve (AUC) and more than twice as many top-10 retrievals. We show that, using these features, the CNN-DTW keyword spotter performs almost as well as the DTW keyword spotter while outperforming a baseline CNN trained only on the keyword templates. The CNN-DTW keyword spotter using BNF-derived CAE features represents an efficient approach with competitive performance suited to rapid deployment in a severely under-resourced scenario.

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。

↑