In spite of decades of research, Automatic Speech Recognition (ASR) is far from reaching the goal of performance close to Human Speech Recognition (HSR). One of the reasons for unsatisfactory performance of the state-of-the-art ASR systems, that are based largely on Hidden Markov Models (HMMs), is the inferior acoustic modeling of low level or phonetic level linguistic information in the speech...

This study examines the coda voicing effect in English on production of preceding vowel by comparing L1 and L2 speech. Particular attention is paid to how coda voicing contrast is encoded in temporal vs. spectral dimensions, how the effect interacts with information structure (with varying focus types), and how the use of information structure differs in L1 vs. L2. Both English (native) and Kor...

We describe a prototype implementation of a representational approach to acoustic-phonetics in knowledge-based speech recognition. Our scheme is based on the 'Speech Sketch', a structure which enables acoustic evidence and phonetic knowledge to be represented in similar ways, so that like can be compared with like. The process of building the Speech Sketch begins with spectrogram image processi...

Title of dissertation: SPEECH RECOGNITION BASED ON PHONETIC FEATURES AND ACOUSTIC LANDMARKS Amit Juneja, Doctor of Philosophy, 2004 Dissertation directed by: Carol Espy-Wilson Department of Electrical and Computer Engineering A probabilistic and statistical framework is presented for automatic speech recognition based on a phonetic feature representation of speech sounds. In this acoustic-phone...

Contemporary psycholinguistic models suggest that there may be two possible routes in phonetic encoding: a 'direct' route which uses stored syllabic units, and an 'indirect' route which relies on the on-line assembly of sub-syllabic units. The computationally more efficient direct route is likely to be used for high frequency words, whereas the indirect route is most likely to be used for novel...

This paper argues that neural networks are good vehicles for automatic speech recognition not simply because they provide non-linear pattern recognition but because their architecture allows the incorporation and exploitation of existing knowledge about speech. The paper is in two parts: Part I defends the need for the incorporation of existing knowledge, while Part II sketches a speech recogni...

Computer-assisted language learning (CALL) is reaching an up most position in the pedagogical field of English as a Second or Foreign Language (ESL/EFL). The present study was carried out to study the effect of using phonetic websites on Iranian EFL students’ pronunciation and knowledge of phonemic symbols. Participants of the study included 30 EFL female pre-intermediate students studyin...

This study explores a multilingual phonotactic approach to automatic language identification using Broadcast News data. The definition of a multilingual phoneset is discussed and an upper limit on the performance of the phonotactic approach is estimated by eliminating any degradation due to recognition errors. This upper bound is compared to automatic language identification based on a phonotac...

Phonological patterns often have phonetic bases. But whether phonetic substance should be encoded in synchronic phonological grammar is controversial. We aim to test the synchronic relevance of phonetics by investigating native Mandarin speakers’ applications of two exceptionless tone sandhi processes to novel words: the contour reduction 213→21/__T (T≠213), which has a clear phonetic motivatio...