Horabail S. Venkatagiri

Efficient keyboard layouts for sequential access in augmentative and alternative communication

The study evaluated the efficiency, measured in typing speed (duration/character) and communication rate (sentence completion time and words/minute), of eight different keyboard layouts using a sequential scanning access method. The two 12-key keyboards tested contained three characters on each key with the second and third characters accessed with a two-key combination. Simulated conversational utterances were used as input to the keyboards and a custom computer program calculated the time and keystroke requirements of each keyboard for each sentence. The 43-key letter-frequency-based arrangement was the most efficient among the keyboards tested, followed closely by 12-key letter-frequency, 43-key alphabetical, and 12- key alphabetical keyboards. The modified QWERTY keyboards were, in comparison, grossly less efficient. The results also show that row-column scanning is nearly twice as fast as linear scanning for all keyboards. Implications of these findings for clinicians and for augmentative and alterna...

Syllable Duration and Pausing in the Speech of Chinese ESL Speakers

* Although suprasegmentals (stress, rhythm, and intonation) and pausing are very important for intelligibility (Anderson-Hsieh, 1992), the literature contains only a few acoustic studies investigating these aspects of speaking proficiency in ESL learners. Bond and Fokes (1985) investigated stress and syllable duration at the word level and found that nonnative speakers representing several language backgrounds showed less differentiation in syllable duration than did native speakers (NSs). Adams (1979) investigated rhythm and pausing at the discourse level in a linguistically heterogeneous group of ESL learners using rhymes and paragraphs as elicitation tasks. She found that the nonnative speakers in her study paused frequently and at inappropriate points in the sentence and differentiated less in duration between stressed and unstressed syllables than did native speakers. However, the studies cited above did not use an independent test to assess speaking proficiency, and they apparently investigated only one level of proficiency-intermediate to high intermediate-so the extent to which more advanced speakers acquire syllable duration and pausing is not known. The preliminary study reported here investigated syllable duration and pausing in Chinese ESL speakers, a group not investigated in the earlier studies but one that has been reported informally as having difficulties with English rhythm (Chang, 1987). We investigated both intermediate-proficiency (IP) and high-proficiency (HP) speakers because comparing such speakers with native speakers should provide information on both the difficulties that Chinese learners have with syllable duration and

Efficiency of lexical prediction as a communication acceleration technique

This study evaluated the performance of a lexical prediction communication program. It showed that lexical prediction saves key/switch activation effort by as much as 50% compared to normal typing. For individuals with significant motor disabilities, the technique may also save on the time required to prepare a message. On the other hand, use by individuals who have significant perceptual deficits may result in an increase in the time required to prepare a message. The study also developed a procedure and a set of indices that may be used to compute quantitative measures of performance of assistive communication devices. The procedure yields a composite performance index that may be useful for “rough and ready” comparison among various AAC devices and techniques. The procedure is especially useful for comparative studies of communication acceleration techniques.

Effect of sentence length and exposure on the intelligibility of synthesized speech

This study investigated the effect of the length of sentences and the amount of exposure to synthesized speech on the intelligibility of a popular text-to-speech (TTS) output device. The results show that sentences with a mean word length of 11 words are as intelligible as sentences with a mean length of approximately 5 words. In augmentative and educational applications of TTS output, it appears that relatively long sentences may be used without fear of adverse impact on intelligibility. The study also shows that there is a large and linear increase in intelligibility with exposure to synthesized speech up to the first 5 sentences heard by listeners within an experimental session. Thereafter, there is a less marked and variable amount of increase in intelligibility up to the next 15 sentences heard. Exposure beyond the first 20 sentences does not appear to contribute to increased intelligibility within a session. Exposure to the Echo II synthesizer over a 3-day period showed that subjects improve signifi...

Effect of window size on rate of communication in a lexical prediction AAC system

The study evaluated the effect of three different “window” sizes (the number of words displayed in the word selection menu) on the efficiency of communication in a lexical prediction augmentative and alternative communication (AAC) program. The results showed that a 15-word window produces significantly higher predictions and fewer keystrokes than a 5-word window. The time required to type the messages was statistically equivalent across windows. However, mean keystroke duration was significantly higher in the 15-word window as compared to the 5-word window. This study shows that (1) a saving in keystrokes does not necessarily result in an increase in the rate of communication in lexical prediction programs; (2) searching a word prediction window for target words places significant cognitive/perceptual demands on even individuals with presumably normal cognitive and perceptual abilities (and probably much more so on AAC users); and (3) a 15-word window produces roughly the same rate of communication as th...

Segmental intelligibility of four currently used text-to-speech synthesis methods

The study investigated the segmental intelligibility of four currently available text-to-speech (TTS) products under 0-dB and 5-dB signal-to-noise ratios. The products were IBM ViaVoice version 5.1, which uses formant coding, Festival version 1.4.2, a diphone-based LPC TTS product, AT&T Next-Gen, a half-phone-based TTS product that uses harmonic-plus-noise method for synthesis, and FlexVoice2, a hybrid TTS product that combines concatenative and formant coding techniques. Overall, concatenative techniques were more intelligible than formant or hybrid techniques, with formant coding slightly better at modeling vowels and concatenative techniques marginally better at synthesizing consonants. No TTS product was better at resisting noise interference than others, although all were more intelligible at 5 dB than at 0-dB SNR. The better TTS products in this study were, on the average, 22% less intelligible and had about 3 times more phoneme errors than human voice under comparable listening conditions. The hybrid TTS technology of FlexVoice had the lowest intelligibility and highest error rates. There were discernible patterns of errors for stops, fricatives, and nasals. Unrestricted TTS output--e-mail messages, news reports, and so on--under high noise conditions prevalent in automobiles, airports, etc. will likely challenge the listeners.

Clinical measurement of rate of reading and discourse in young adults

Abstract The present study investigated discourse (connected speech) rates and utterance rates in a group of normal-speaking subjects. Sample sizes of about 100 words (140 syllables), 120 words (165 syllables), and 112 words (143 syllables) were found to be sufficient to obtain valid estimation of rate of reading, talking, and describing, respectively. The slow speakers in the group had rates of 174–186 words per minute (WPM) or 241–259 syllables per minute (SPM), 136–144 WPM (183–204 SPM), 133–147 WPM (171–181 SPM) during reading, talking, and picture description, respectively. These rates may be appropriate guidelines for rate control therapies of stuttering. If individual utterances rather than connected speech are used for rate control, 3.35–3.67 words per second (WPS) or 4.54–5.07 syllables per second (SPS), 2.28–3.09 WPS (3.36–4.19 SPS), 2.61–3.12 WPS (3.27–3.96 SPS), falling between the 25th and 50th percentile values, appear to be suitable for reading, talking, and picture description tasks respectively. In the present study, the rates of reading and discourse (talking about self and picture description) were comparable whether measured in WPM or SPM and in males and females.

The Quality of Digitized and Synthesized Speech: What Clinicians Should Know

This paper reviews factors contributing to the quality of digitized and synthesized speech. Digital recording and playback of speech generally produces highly intelligible and natural-sounding spee...

Segmental Intelligibility of Three Text-to-Speech Synthesis Methods in Reverberant Environments

In this study, the segmental intelligibility of three currently available text-to-speech products under two reverberant conditions was investigated. The reverberation times used were 1.2 and 2.4 s simulating reverberation that may exist in a large room and a large hall with poor acoustics. The human speech had an overall intelligibility (whole words correct) of 95% and a phoneme error rate of 2.35% under reverberant conditions investigated in this study, which were not significantly different from those obtained in a nonreverberant controlled condition. In contrast, the overall intelligibility of text-to-speech voices was 68% and phoneme error rate was 14.48%, which indicated that that text-to-speech output suffers significantly in the same reverberant conditions. Implications of these findings for the improvement of text-to-speech products and the practice of AAC are discussed with suggestions for further research.

Techniques for Enhancing Communication Productivity in AAC: A Review of Research.

This paper summarizes selected findings on approaches to increasing the rate of communicatively appropriate responses in augmentative and alternative communication (AAC). Six approaches—efficient k...