Purpose The number of older persons in industrialized countries is steadily increasing. Seniors living alone are more numerous, and we must find solutions that will allow them to continue to stay at home comfortably and safely. Smart housings can be one of these solutions. One of the biggest challenges in ambient assisted living (AAL) is to develop smart homes that anticipate and respond to the needs of the inhabitants. Given the diverse profiles of the older adult population, it will therefore be essential to facilitate interaction with the smart home through systems that respond naturally to voice commands rather than using tactile interfaces. Method The first step in our study was to evaluate how well ambient assistive speech technology is received by the target population. We report on a user evaluation assessing acceptance and fear of this new technology. The experiment aimed at testing three important aspects of speech interaction: voice command, communication with the outside world, home automation system interrupting a person's activity. Participants were 7 older persons (71-88 years old), 7 relatives and 3 professional carers; the experiments were conducted in a smart home with a voice command using a Wizard-of-Oz technique. The second step in our study was related to the adaptation of speech recognition technologies to the older adult population. Judging by the literature this has not been extensively studied. In fact, it is known that industrialized speech recognition system models are not adapted to seniors but to other categories of the population. In order to do this we recorded a specific speech corpus (voice-age) with 7 older adults (70 to 89 years old) reading sentences (a total of 4 hours of speech). A second corpus (ERES38) of free talking (18 hours of speech) was recorded by 23 speakers (68-98 years old). These corpora were analyzed in a semi-automatic manner to reveal the aged-voice characteristics. Results & Discussion Regarding the technical aspect, it appears that some phonemes are more affected by age than others. Thus, a specific adaptation of the acoustic models for ASR is required. Regarding the acceptance aspect, voice interfaces appear to have a great potential to ease daily living for older adults and frail persons and would be better accepted than other, more intrusive, solutions. By considering still healthy and independent older persons in the user evaluation, one interesting finding was overall acceptance provided the system is not conducive to a lazy lifestyle by taking control of everything. This particular concern must be addressed in the development of smart homes that support daily living by stressing the ability to control the daily routine rather than altering it. This study shows the great interest of voice interfaces to develop efficient solution to enable the growing number of older persons to continue to live in their own homes as long as possible.

This paper presents a system to recognize distress speech in the home of seniors to provide reassurance and assistance. The system is aiming at being integrated into a larger system for Ambient Assisted Living (AAL) using only one microphone with a fix position in a non-intimate room. The paper presents the details of the automatic speech recognition system which must work under distant speech condition and with expressive speech. Moreover, privacy is ensured by running the decoding on-site and not on a remote server. Furthermore the system was biased to recognize only set of sentences defined after a user study. The system has been evaluated in a smart space reproducing a typical living room where 17 participants played scenarios including falls during which they uttered distress calls. The results showed a promising error rate of 29% while emphasizing the challenges of the task.