Analysis of Listeners’ Summaries of Synthesized Speech Passages
نویسندگان
چکیده
The purpose of this investigation was to specify the kinds of miscomprehensions produced by individuals listening to synthetic speech. In the first study, 80 written summaries of synthesized speech passages were analyzed to determine the types of miscomprehensions or linguistic departures made by listeners when attempting to recall the spoken texts. These departures were classified according to their linguistic departure type (insertion, recast, reduction, substitution, paraphrase) and level (phonemic, lexical, phrase, clause, discourse). Linguistic departures were studied as to their role in miscomprehension and their ability to reveal listener comprehension strategies. In a second study, 159 written summaries were analyzed according to their primary departure type and then analyzed for their relation to speech synthesis voice quality, presentation rate, and scores from a global rating of discourse summarization accuracy. Three “clusters” emerged from these analyses, reflecting an association between specific linguistic departures with the above variables. Research and clinical implications of the linguistic departure procedure are discussed.
منابع مشابه
بررسی وضوح گفتار کودکان فلج مغزی اسپاستیک 8 تا 12 ساله
Background and purpose: Speech intelligibility refers to how speech is understandable by listeners. This study examined speech intelligibility in children (Persian native speakers) with spastic cerebral palsy aged 8-12 years old. Materials and methods: A cross-sectional study was performed in 31dysarthric students (….. boys and …..girls) in Tehran, 2014. A list of w...
متن کاملWord segmentation in Persian continuous speech using F0 contour
Word segmentation in continuous speech is a complex cognitive process. Previous research on spoken word segmentation has revealed that in fixed-stress languages, listeners use acoustic cues to stress to de-segment speech into words. It has been further assumed that stress in non-final or non-initial position hinders the demarcative function of this prosodic factor. In Persian, stress is retract...
متن کاملMinimizing Word Error Rate in Textual Summaries of Spoken Language
Automatic generation of text summaries for spoken language faces the problem of containing incorrect words and passages due to speech recognition errors. This paper describes comparative experiments where passages with higher speech recognizer confidence scores are favored in the ranking process. Results show that a relative word error rate reduction of over 10% can be achieved while at the sam...
متن کاملComparison of objective and subjective measures of speech intelligibility in elderly hearing-impaired listeners.
Three experiments were performed to evaluate the use of subjective intelligibility estimations as a method for measuring hearing aid benefit. Subjective and objective speech intelligibility scores were compared for young normal-hearing and elderly hearing-impaired listeners. Objective intelligibility scores were obtained using the Connected Speech Test (CST). This test consists of conversationa...
متن کاملExposure to multiple accents supports infants' understanding of novel accents.
Accented speech poses a challenge for listeners, particularly those with limited knowledge of their language. In a series of studies, we explored the possibility that experience with variability, specifically the variability provided by multiple accents, would facilitate infants' comprehension of speech produced with an unfamiliar accent. 15- and 18-month-old American-English learning infants w...
متن کامل