Our corpus consists of Greek fricatives from five places of articulation and two voicing values produced in nonce disyllabic words before in stressed syllables (e.g., ).
In the current study, we explore the factors underlying the well-known difficulty in acoustic classification of front fricatives (McMurray & Jongman, 2011 Maniwa et al., 2009) by taking a closer look at the production of 29 native Greek speakers.
Research studies should inform how and when those living with MND are introduced to voice banking. CONCLUSIONS: Voice banking services should be more widely promoted to ensure that individuals can consider voice banking prior to changes in their speech. Support from professionals was noted by some as being key. Those completing the process viewed the personalised voices positively and all were used when created. The time taken to complete the process had a large variation. RESULTS: Less than half of the clients whose notes were reviewed had been informed about voice banking, one in four had completed the voice banking process, around half were using communication aids, and one in ten were using their personalised synthetic voice on a communication aid. Responses to a routine follow up survey were also collated. Case notes were reviewed to extract information about use of communication aids, offer of voice banking, and use of synthesised speech. METHOD: A service review of existing health records from neurological services in Sheffield, UK, carried out retrospectively and covering 20. OBJECTIVE: To review a dedicated voice banking service with the aim of informing service development. Little is known about how best to support this process. 1 DemonstrationīACKGROUND: Voice banking allows those living with Motor Neurone Disease (MND) to create a personalised synthetic voice. The system facili3 tates the recording and labeling of large cor3 pora of speech, making it useful for speech and linguistic research, and it provides imme3 diate feedback on pronunciation, thus making it useful as a clinical learning tool. The interface may prove useful for other purposes as well.
Ultimately, the recorded corpus and the resulting speech da3 tabase is used for concatenative synthetic speech, thus allowing individuals at home or in clinics to create a synthetic voice in their own voice. The system's intention is to make the process of recording a corpus of ut3 terances relatively easy for those inexpe3 rienced in linguistic analysis. Recordings are automatically labeled and saved and a speech database is created from these recordings. Users can then rerecord an unacceptable utterance. Each recording is screened for pitch, amplitude and pronuncia3 tion and users are given immediate feedback on the acceptability of each recording. The system then prompts users with both visual (text3based) and auditory prompts. The system guides users through an au3 tomatic calibration process that sets pitch, amplitude, and silence. We will demonstrate the ModelTalker Voice Recorder (MT Voice Recorder) - an interface system that lets individuals record and bank a speech database for the creation of a synthetic voice.
0 kommentar(er)
