Examples of passages in the text that was excluded were utterances regarding the time following the death of the older relative such as the arrangements for the funeral or the next of kin's own situation and grief following the loss of a relative.
We will now explain the main choices we made for our system regarding utterance selection and utterance verification procedures.
Regarding utterance contents, three dictionaries were constructed: medical, emotional, and social.
Regarding utterance types, communication used during consultations was analyzed with the dictionaries included in the LaComm.
Ten voiced utterances are regarded as targets.
However, in the total variability space estimation, a given speaker's entire set of utterances is regarded as having been produced by different speakers.
If we suppose that a given target language's entire set of utterances is regarded as having been produced by different languages, a common pool of hidden variables acts as basis factors and represents the utterances from different languages.
We estimate the language total variability space by using the dataset shown in Section 5, and we suppose that a given target language's entire set of utterances is regarded as having been belonging to different language.
Regarding utterances types, communication used during consultations was analysed with the dictionaries included in the LaComm.
Regarding utterances' contents, three dictionaries were constructed (medical, emotional and social).
All utterances were further automatically analyzed regarding a comprehensive set of acoustic measures related to F0, intensity, formants, voice source, and temporal characteristics of speech.
