Abstract: A new form of augmentative and alternative communication device for people with severe speech impairment- the voice-input voice-output communication (VIVO). It recognizes the disordered speech of the user and builds messages, which are converted into artificial speech. Application development was accepted to employ the user-centred design and progress methods, which well-known and sophisticated key requirements for the tool. A new method for building small words, speaker-dependent automatic speech generates with reduced amounts of guidance data, was applied. The device is also capable of doing optimized searching. The voice input is used as search keyword and converted into the text first. This text is then given for searching over internet or with some predefined domains. The output obtained is optimized data and is then again converted into the voice output. The VIVO was evaluated to make use of the device to produce intelligible speech output from disordered speech input and also to use it as the question answering device. The trial highlighted some issues which limit the performance and usability of the device when applied in real usage situations, with mean recognition accuracy of 67% in these condition. These limits will be addressed in future work.

Keywords: VIVO, TTS