A recent development in the field of technical aids for the handicapped is electronic speech synthesis. Whereas this revolutionary advancement may have many benefits for persons whose speech is defective or for those individuals who have lost the use of their natural speech apparatus through physical trauma, a satisfactory analysis of language training models applicable to the instruction of the Phonic Mirror Handivoice model HC 120 had not yet been accomplished. In the present study, two non-vocal cerebral palsied subjects participated throughout a series of three experiments. It was considered important to examine intensively the performances of these selected individuals as they interacted with and learned about the various aspects of a unique form of vocal behavior. In the first experiment, a traditional paired-associates procedure, Method A, was the standard training method with which other methods were compared. Method B was essentially a paired-associates procedure that emphasized the personal histories of verbal behavior for each subject; Method C established discriminative control over vocal responses by natural features of the environment; Method D combined a paired-associates procedure with one in which the subject directly supplied supplementary verbal stimuli as part of the training procedure. The criterion for effectiveness was the number of training/testing cycles required for each S to achieve criterion (of 100% correct) on each word list. The results of these comparisons indicated that none of the three methods was any more or less effective than the traditional paired-associates procedures. Upon the completion of the second comparison (i.e., Method A and Method C), an informal retention survey was conducted. The responses from both subjects to this survey indicated poor retention for test stimuli established on early lists but increasing retention on the more recently trained lists. Experiment 2 was therefore designed to determine the replicability of this retention phenomenon both within and between the two S's, using Method A, across three different word lists. This experiment showed that when test stimuli were presented 24 hours after training, there was little or no loss of control over the appropriate word. An additional finding was that little or no retention was exhibited by either S for words which had not been retested at the 24 hour interval and whose retest intervals were 4, 5, and 6 days. A feature of the Experiment 2 survey was that the variables of time (elapsed from training to testing) and additional training were confounded. Therefore, Experiment 3, again using Method A, was conducted to separately (1)evaluate the effectiveness of a simple retraining procedure on extended retention, and (2)examine the effect of elapsed time on discriminative control over the previously established verbal responses. The results of the retraining procedure were positive. Whereas previous surveys of Experiment 2 had produced little or no evidence of retention beyond the 48 hour interval, 60% of the test stimuli in Experiment 3 discriminated their appropriate verbal responses. In contrast, the word lists which had not undergone retraining at the 24 hour interval nor had been followed by additional training of new word lists exhibited retention of either 0 or 20%. Two major outcomes of the present study were (1)the four training methods were all effective, but not differentially so, in teaching the numeric language of the HandiVoice, and (2)effective retention over a number of days could be achieved by a single retraining session. These findings offer several practical guidelines for future HandiVoice instructors to establish and maintain a new but important form of verbal behavior.

No description available.

With the wide-spread adoption of hypermedia systems and the World Wide Web (WWW) in particular, these systems have evolved from simple systems with only textual content to those that incorporate a large content base, which consists of a wide variety of document types. Also, with the increase in the number of users, there has grown a need for these systems to be accessible to a wider range of users. Consequently, the growth of the systems along with the number and variety of users require new presentation and navigation mechanisms for a wider audience. One of the new presentation methods is the audio-only presentation of hypertext content and this research proposes a novel solution to this problem for complex and dynamic systems. The hypothesis is that the proposed Audio Browser is an efficient tool for presenting hypertext in audio format, which will prove to be useful for several applications including browsers for visually-impaired and remote users. The Audio Browser provides audio-only browsing of contents in a Petri-based hypertext system called Context-Aware Trellis (caT). It uses a combination of synthesized speech and pre-recorded speech to allow its user to listen to contents of documents, follow links, and get information about the navigation process. It also has mechanisms for navigating within documents in order to allow users to view contents more quickly.

No description available.

This thesis comprises investigations of the perceptual consequences of children’s misarticulated speech – as perceived by clinicians, by everyday listeners, and by the children themselves. By inviting methods from other areas to the study of speech disorders, this work demonstrates some successful cases of cross-fertilization. The population in focus is children with a phonological disorder (PD), who misarticulate /t/ and /k/. A theoretical assumption underlying this work is that errors in speech production are often paralleled in perception, e.g. that children base their decision on whether a speech sound is a /t/ or a /k/ on other acoustic-phonetic criteria than those employed by proficient language users. This assumption, together with an aim at stimulating self-monitoring in these children, motivated two of the included studies. Through these studies, new insights into children’s perception of their own speech were achieved – insights entailing both clinical and psycholinguistic implications. For example, the finding that children with PD generally recognize themselves as the speaker in recordings of their own utterances lends support to the use of recordings in therapy, to attract children’s attention to their own speech production. Furthermore, through the introduction of a novel method for automatic correction of children’s speech errors, these findings were extended with the observation that children with PD tend to evaluate misarticulated utterances as correct when just having produced them, and to perceive inaccuracies better when time has passed. Another theme in this thesis is the gradual nature of speech perception related to phonological categories, and a concern that perceptual sensitivity is obscured in descriptions based solely on discrete categorical labels. This concern is substantiated by the finding that listeners rate “substitutions” of [t] for /k/ as less /t/-like than correct productions of [t] for intended /t/. Finally, a novel method of registering listener reactions during the continuous playback of misarticulated speech is introduced, demonstrating a viable approach to exploring how different speech errors influence intelligibility and/or acceptability. By integrating such information in the prioritizing of therapeutic targets, intervention may be better directed at those patterns that cause the most problems for the child in his or her everyday life. / <p>QC 20140317</p>

No description available.

No description available.

This thesis proposes to improve and enrich the expressiveness of English Text-to-Speech (TTS) synthesis by identifying and generating natural patterns of prosodic prominence. In most state-of-the-art TTS systems the prediction from text of prosodic prominence relations between words in an utterance relies on features that very loosely account for the combined effects of syntax, semantics, word informativeness and salience, on prosodic prominence. To improve prosodic prominence prediction we first follow up the classic approach in which prosodic prominence patterns are flattened into binary sequences of pitch accented and pitch unaccented words. We propose and motivate statistic and syntactic dependency based features that are complementary to the most predictive features proposed in previous works on automatic pitch accent prediction and show their utility on both read and spontaneous speech. Different accentuation patterns can be associated to the same sentence. Such variability rises the question on how evaluating pitch accent predictors when more patterns are allowed. We carry out a study on prosodic symbols variability on a speech corpus where different speakers read the same text and propose an information-theoretic definition of optionality of symbolic prosodic events that leads to a novel evaluation metric in which prosodic variability is incorporated as a factor affecting prediction accuracy. We additionally propose a method to take advantage of the optionality of prosodic events in unit-selection speech synthesis. To better account for the tight links between the prosodic prominence of a word and the discourse/sentence context, part of this thesis goes beyond the accent/no-accent dichotomy and is devoted to a novel task, the automatic detection of contrast, where contrast is meant as a (Information Structure’s) relation that ties two words that explicitly contrast with each other. This task is mainly motivated by the fact that contrastive words tend to be prosodically marked with particularly prominent pitch accents. The identification of contrastive word pairs is achieved by combining lexical information, syntactic information (which mainly aims to identify the syntactic parallelism that often activates contrast) and semantic information (mainly drawn from the Word- Net semantic lexicon), within a Support Vector Machines classifier. Once we have identified patterns of prosodic prominence we propose methods to incorporate such information in TTS synthesis and test its impact on synthetic speech naturalness trough some large scale perceptual experiments. The results of these experiments cast some doubts on the utility of a simple accent/no-accent distinction in Hidden Markov Model based speech synthesis while highlight the importance of contrastive accents.

Thesis (M.S.)--Rochester Institute of Technology, 1989. / Includes bibliographical references (leaves 81-85).

Thesis (M.Sc.)--University of Alberta, 2009. / Title from PDF file main screen (viewed on July 30, 2009). "A thesis submitted to the Faculty of Graduate Studies and Research in partial fulfillment of the requirements for the degree of Master of Science, Department of Computing Science, University of Alberta." Includes bibliographical references.