Second International Conference on Spoken Language Processing (ICSLP'92)

Banff, Alberta, Canada
October 13-16, 1992

The PSH/DISPE Helium Speech Cdrom

Alain Marchal (1), C. Meunier (1), P. Gavarry (2)

(1) Laboratoire Parole et Langage, URA 261 CNRS, Universite de provence, Aix-en-Provence, France
(2) Institut National de Plongee Professionelle, Port de la Pointe Rouge, Marseille, France

Gas mixture and pressure modify the spectral characteristics of diver's speech. Additionnally, constraints imposed on jaw movements by wearing a facial mask affect the speech production process. The auditory feedback loop is equally concerned. Furthermore, underwater adverse working conditions are characterised by noise from different sources. As a result, divers' speech is poorly intelligible and communications between divers and surface control need to be enhanced. To this end, «voice unscramblers» are being used. However, the technological state of commercially available equipment is dated and the quality of speech remains insufficient. To help with the design, testing and qualification of new communication devices, a bilingual (French-English) Data-base is set up. It consists of phonetically balanced lists of 200 words read by 17 divers under sea and in chambers at operationnal levels from the surface to 300m.These recordings have been edited, labelled and then stored on a CD-ROM. The PSH/DISPE CDROM complies with the SAM EUROPEC standards (ESPRIT-SAM project n°2589). It consists of acoustic signal files (40 KHz, 16 bits) of hyperbaric speech and of associated files. These later ones provide informations about the speakers and the recording conditions.

Full Paper

Bibliographic reference.  Marchal, Alain / Meunier, C. / Gavarry, P. (1992): "The PSH/DISPE helium speech cdrom", In ICSLP-1992, 1657-1660.