Example-based speech enhancement is a promising singlechannel approach for coping with highly nonstationary noise. Given a noisy speech input, it first searches in a noisy speech corpus for the noisy speech examples that best match the input. Then, it concatenates the clean speech examples that are paired with the matched noisy examples to obtain an estimate of the underlying clean speech compo...

Speaker’s intentions can be represented into domain actions (domainindependent speech acts and domain-dependent concept sequences). Therefore, domain action classification is very useful to a dialogue system that should catch user’s intention in order to generate correct reaction. In this paper, we propose a neural network model to determine speech acts and concept sequences at the same time. T...

Research on “zero resource” speech processing focuses on learning linguistic information from unannotated, or raw, speech data, in order to bypass the expensive annotations required by current speech recognition systems. While most recent zero-resource work has made use of only speech recordings, here, we investigate the use of visual information as a source of weak supervision, to see whether ...

This study was intended first to categorize the L2 learners in terms of their learning style preferences and second to investigate if their learning preferences are related to lexical inferencing. Moreover, strategies used for lexical inferencing and text related issues of text density and parts of speech were studied to determine their moderating effects and the best predictors of lexical infe...

The aim of this work is to improve the recognition performance of spontaneous speech. In order to achieve the purpose, the authors of this chapter propose new approaches of unsupervised adaptation for spontaneous speech and evaluate the methods by using diagonal-covariance and full-covariance hidden Markov models. In the adaptation procedure, both methods of language model (LM) adaptation and a...