论文标题
无监督的声学单元发现的潜在Dirichlet分配的时间扩展
A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery
论文作者
论文摘要
潜在的Dirichlet分配（LDA）广泛用于一组文档的无监督主题建模。模型中没有使用时间信息。但是，连续令牌的相应主题之间通常存在关系。在本文中，我们为LDA提供了一个扩展名，该扩展名使用马尔可夫链来建模时间信息。我们将这种新模型从语音发现进行声学单元发现。作为输入令牌，该模型从具有512个代码的矢量定量（VQ）神经网络中对语音进行了离散的编码。然后，目标是将这512个VQ代码映射到50个类似电话的单元（主题），以使其更加类似于真实的电话。与基本LDA相反，该基础LDA仅考虑VQ代码在发音（文档）中的共发生方式，Markov Chain LDA还捕获了连续代码如何彼此跟随。与基本LDA相比，这种扩展会导致集群质量和电话分割结果的提高。与最近学习50个单元的媒介量化神经网络方法相比，扩展的LDA模型在电话分割方面的性能较好，但在相互信息中的性能较差。
Latent Dirichlet allocation (LDA) is widely used for unsupervised topic modelling on sets of documents. No temporal information is used in the model. However, there is often a relationship between the corresponding topics of consecutive tokens. In this paper, we present an extension to LDA that uses a Markov chain to model temporal information. We use this new model for acoustic unit discovery from speech. As input tokens, the model takes a discretised encoding of speech from a vector quantised (VQ) neural network with 512 codes. The goal is then to map these 512 VQ codes to 50 phone-like units (topics) in order to more closely resemble true phones. In contrast to the base LDA, which only considers how VQ codes co-occur within utterances (documents), the Markov chain LDA additionally captures how consecutive codes follow one another. This extension leads to an increase in cluster quality and phone segmentation results compared to the base LDA. Compared to a recent vector quantised neural network approach that also learns 50 units, the extended LDA model performs better in phone segmentation but worse in mutual information.
