The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...
We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that ...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
We assess the current state of the art in speech summarization, by comparing a typical summarizer on two different domains: lecture data and the SWITCHBOARD corpus. Our results ca...
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...