Abstract A typical large vocabulary automatic speech recognition (ASR) system consists of three main components: 1) the feature extraction, 2) the pattern classification, and 3) the language modeling. Replacing hardwired prior knowledge in the pattern[…]
Abstract As computing and communications continue to converge, on-line access to large databases of audio and video becomes increasingly possible. However, searching this kind of material by content is difficult since unlike conventional documents, there[…]
Abstract The perception of speech reflects both a stimulus driven process and influences from the mental lexicon. Some of the lexical influences, such as phoneme restoration, are well known. The focus of this presentation will[…]
Abstract Syllable structure is postulated in an effort to explain in unified fashion three distinct domains of facts:Syllabic Intuitions: Speakers appear to have reliable knowledge of syllable count and syllable divisionsProsodic Peaks: Some recurrent strings[…]
Abstract Parallel corpora — collections of text in parallel translation — play an important role in current work on statistical models of machine translation, cross-language information retrieval, and acquisition of lexical resources for multilingual natural[…]
http://vimeo.com/54571774 View Seminar Video Abstract We model the transfer of information from one cell to another via a generalization of the Shannon-Blackwell billiard ball channel. Applying information and decision theory to this model, we determine[…]
http://vimeo.com/32812304 View Seminar Video Abstract Speech perception involves the parallel processing of a wide range of information. Audiovisual speech perception is the best example of this parallel processing with the visual modality providing complementary information[…]
