Search Results

Honda, working closely with IBM for their model year 2009 introduction, will be releasing the next step in the evolution of speech user interfaces in vehicles. The new Honda vehicles will include the leading edge Free Form Command (FFC) technology developed by IBM as part of its IBM Embedded ViaVoice (EVV) product line. At its core, Free Form Commands improve the overall end-user experience by creating a system that is easier to use out of the box by increasing the overall usability of the system. Free Form Commands employ an innovative approach which allows Statistical Language Model technology to be deployed within the constraints of an embedded computing environment. This technology allows users to speak commands that are not part of a predefined fixed set of phrases, as is required in today’s vehicles, but instead speak command phrases that match the application functional area they are targeting.

This paper will focus on the technology improvements and development effort required to enable human sounding system responses and voice enablement for destination entry for automotive navigation systems. Honda and IBM have been working together since around 1999. The first product to reveal the fruits of this relationship was the 2003 Accord. Voice enablement consists of speech recognition of a Radio/Audio, Climate Control, or Navigation related command, and providing voice responses using a combination of prerecorded messages combined with Text-To-Speech (TTS) generated outputs. The Accord in 2003 used a combination of high quality prerecorded prompts with occasional use of TTS synthesis. The 2005 Acura RL and Odyssey introduced use of Concatenative (human sounding) TTS. This paper will discuss the trade-offs and design considerations for the use of Concatenative TTS as opposed to Formant TTS technology.