This paper proposes an approach to detect social speech signals by computing segmental features using adaptation of segmental Hidden Markov Models (HMMs). This approach uses segmental HMMs and model adaptation techniques such as Maximum Likelihood Linear Regression (MLLR) and Maximum A Posterior (MAP) in order to acquire specific (or adapted) segmental HMMs that are fine-tuned to detect local r...

This paper presents the first online biofeedback speech training tool for Greek designed to offer training on the production and perception of segmental and suprasegmental aspects of Greek. It is addressed to learners of Greek as an L2 and to clinical populations with articulation and phonation problems. The tool comprises four components: (i) the Phonetic Library, i.e., the acoustic, articulat...

This study examined listeners' endorsement of cognitive, linguistic, segmental, and suprasegmental strategies employed when listening to speakers with dysarthria. The study also examined whether strategy endorsement differed between listeners who earned the highest and lowest intelligibility scores. Speakers were eight individuals with dysarthria and cerebral palsy. Listeners were 80 individual...

This study is a phonetic investigation of six Cantonese L1-English L2 students living in Englishspeaking countries. The students were recorded three times during their first year abroad: before immigration, at six months, and at one year. Phonetic details from the three recordings have been measured and compared. Preliminary results suggest gradual but significant phonological reorganization du...

The perceived impression that a spoken utterance is not native is due to the culmination of a combination of segmental and suprasegmental phonological and phonetic characteristics entrenched in the speakers native language (L1) or it results from different types of interplay between those characteristics of the L1 and the second (or foreign) language (L2). The present paper reports findings of ...

The speech-perception ability reported from profound hearing impaired persons using different technical aids: hearing aids, cochlear implants, or tactile aids, varies widely. A test-battery was constructed that consisted of segmental and suprasegmental tasks and speech tracking. Two presentation modalities were used, vision only and visual information supplemented with the assistive device. Dea...

This study examined perceived degrees of foreign accent using speech of second language learners and native speakers morphed to each other in terms of three suprasegmental parameters. Results indicated that duration and f0, but not intensity, are central to accuracy and accentedness of a simple Japanese sentence. The effects of these two parameters still existed even when we evaluate only ‘accu...

The speech perception ability reported from profoundly hearing-impaired persons using hearing aids or cochlear implants varies widely. A test battery was constructed that consisted of segmental and suprasegmental tasks and connected speech presented in three digerent modalities: visual (V), auditive (A) and audiovisual (AV). Two groups of patients participated. Fifeen subjects with a profound h...