Thesis (B.Sc)--University of Hong Kong, 2001. / "A dissertation submitted in partial fulfilment of the requirements for the Bachelor of Science (Speech and Hearing Sciences), The University of Hong Kong, May 4, 2001." Also available in print.

Thesis (B.Sc)--University of Hong Kong, 2002. / "A dissertation submitted in partial fulfilment of the requirements for the Bachelor of Science (Speech and Hearing Sciences), The University of Hong Kong, May 10, 2002." Also available in print.

Thesis (Ph. D.)--Syracuse University, 2005. / "Publication number AAT 3194015."

Thesis (Ph. D.)--Ohio State University, 1972. / Includes vita. Includes bibliographical references (leaves 72-75). Available online via OhioLINK's ETD Center.

Thesis (Ph. D.)--University of Washington, 2006. / Vita. Includes bibliographical references (leaves 215-230).

A number of aspects of speech training involve assessing the quality of the student's speech. It is of interest to determine whether such speech quality analysis can be done automatically. This thesis provides a preliminary answer to that question by proposing and then evaluating a set of quality measures for comparing the quality of two segments of speech. Speech quality is taken to be the lack of defects in the articulatory and prosodic components of speech. It is a non-quantitative definition from speech pathology that can meet the needs of speech training. Speech defects common among deaf children and students of English as a second language are reviewed, and classified according to this scheme. The speech quality measures are based on a linear prediction model of speech, and adapt several techniques from the field of speech recognition. Evaluations using speech with known quality defects show that the articulatory measures are effective in detecting most of the common errors of articulation, with the exception of ones between nasal sounds. The prosodic quality measures of loudness and timing give very useful indications of syllable stress and voicing errors. The timing measure is derived from the optimal time-warping curve between the two utterances, and provides an accurate means of tracking speed variations in speech. Differences between speakers tend to mask articulatory quality errors, but have little effect on the prosodic quality measures. An articulatory distance measure is proposed that partly counters these interspeaker differences. Work remains to be done in a number of key areas, but the results of this preliminary investigation suggest that automatic speech quality analysis by computer is practical and may one day become a versatile tool for speech training. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Unknown

Language assessment of children is an essential task of the speech clinician and many studies have been concerned with the validity of the data gathered. Few studies, however, have investigated examiner variability as a possible source of deviation in language assessment. This study was designed to evaluate and compare the amount of verbal output which children with normal language use when examined by two different examiners when the examiners are in their most comfortable setting. Six children, four years of age, were examined by a speech pathologist in the clinic and the mother in the home and the 12 fifteen-minute taped episodes of dialogue were transcribed and subjected to mean length of response analysis by the Wilcoxon Matched-Pair Signed-Rank test of significance. Results indicate there is no statistical significance at the .05 level of confidence to the differences between results obtained by the examiners nor to the differences in results obtained between the first and second examination. The average MLR achieved by the subjects in this study does not reach those of previously established norms. A trend was evidenced for the speech pathologist to elicit greater amount of verbal output than the mothers and both the statistical non-significance of differences and the failure to reach previous norms may be an artifact due to the small sample size, method of recording, and examiner variability.

No description available.

No description available.

No description available.