The prevalent state of the art in spoken language understanding by spoken dialog systems is both modular and whole-utterance. It is modular in that incoming utterances are processed by independent components that handle different aspects, such as acoustics, syntax, semantics, and intention / goal recognition. It is whole-utterance in that each component completes its work for an entire utteranc...

This paper expands a previously proposed universal acoustic characterization approach to spoken language identification (LID) by studying different ways of modeling attributes to improve language recognition. The motivation is to describe any spoken language with a common set of fundamental units. Thus, a spoken utterance is first tokenized into a sequence of universal attributes. Then a vector...

This study presents the first experimental evidence that singing can facilitate short-term paired-associate phrase learning in an unfamiliar language (Hungarian). Sixty adult participants were randomly assigned to one of three "listen-and-repeat" learning conditions: speaking, rhythmic speaking, or singing. Participants in the singing condition showed superior overall performance on a collectio...

Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabulary Continuous Speech Recognition (LVCSR) decoder, a text-based ad hoc retrieval method can be applied directly to the transcribed documents. However, recognition errors will significantly degrade the retrieval performa...

For language modeling of spontaneous speech recognition, we propose a style transformation approach, which transforms written texts to a spoken-style language model. Since these two styles are largely different and thus direct transformation is difficult, we cascade two transformation methods; rule-based transformation to rewrite written-style texts to intermediate “verbatim” texts, and statist...

There is a strong relationship between evaluation and methods for automatically training language processing systems, where generally the same resource and metrics are used both to train system components and to evaluate them. To date, in dialogue systems research, this general methodology is not typically applied to the dialogue manager and spoken language generator. I will argue that any metr...