Bootstrapping a spoken language identification system using unsupervised integrated sensing and processing decision trees

Abstract

Abstract-In many inference and learning tasks, collecting large amounts of labeled training data is time consuming and expensive, and oftentimes impractical. Thus, being able to efficiently use small amounts of labeled data with an abundance of unlabeled data-the topic of semi-supervised learning (SSL) [1]-has garnered much attention. In this paper, we look at the problem of choosing these small amounts of labeled data, the first step in a bootstrapping paradigm. Contrary to traditional active learning where an initial trained model is employed to select the unlabeled data points which would be most informative if labeled, our selection has to be done in an unsupervised way, as we do not even have labeled data to train an initial model.We propose using unsupervised clustering algorithms, in particular integrated sensing and processing decision trees (ISPDTs) [2], to select small amounts of data to label and subsequently use in SSL (e.g. transductive SVMs). In a language identification task on the CallFriend 1 and 2003 NIST Language Recognition Evaluation corpora [3], we demonstrate that the proposed method results in significantly improved performance over random selection of equivalently sized training data.

Keyword spotting in singing with duration-modeled HMMs

“…As mentioned in the conclusion, a big hindrance to our research is the small size of our data set. We would therefore like to expand this data set, possibly by using a bootstrapping mechanism [23]. As shown in [14], tri-phone models often provide better results than the monophone models used by us.…”