Speech Corpus Spoken by Young-old, Old-old and Oldest-old Japanese

Speech Corpus Spoken by Young-old, Old-old and Oldest-old Japanese Yurie Iribe1, Norihide Kitaoka2 and Shuhei Segawa3 1School of Information Science and Technology, Aichi Prefectural University 1522-3 Ibaragabasama, Nagakute, Japan 2Department of Information Science and Intelligent Systems, Tokushima University 2-1, Minamizyousanzima, Tokushima, Japan 3Graduate School of Information Science, Nagoya University Furo-cho, Chikusa-ku, Nagoya, Japan iribe@ist.aichi-pu.ac.jp, kitaoka@is.tokushima-u.ac.jp, segawa.shuhei@g.sp.m.is.nagoya-u.ac.jp Abstract We have constructed a new speech data corpus, using the utterances of 100 elderly Japanese people, to improve speech recognition accuracy of the speech of older people. Humanoid robots are being developed for use in elder care nursing homes. Interaction with such robots is expected to help maintain the cognitive abilities of nursing home residents, as well as providing them with companionship. In order for these robots to interact with elderly people through spoken dialogue, a high performance speech recognition system for speech of elderly people is needed. To develop such a system, we recorded speech uttered by 100 elderly Japanese, most of them are living in nursing homes, with an average age of 77.2. Previously, a seniors’ speech corpus named S-JNAS was developed, but the average age of the participants was 67.6 years, but the target age for nursing home care is around 75 years old, much higher than that of the S-JNAS samples. In this paper we compare our new corpus with an existing Japanese read speech corpus, JNAS, which consists of adult speech, and with the above mentioned S-JNAS, the senior version of JNAS. Keywords: elderly speech corpus, nursing home care, speech corpus construction, speech recognition 1. Introduction Previous research suggests that elderly people have more difficulty using information and communication technology (ICT) than younger adults (Júdice, 2010). The main reasons for this are the complexity of existing user interfaces and the limited set of available interaction modalities, since this technology is mainly being designed with younger users in mind. Hence, from the point of view of ICT, adapting the technology to better suit the needs of the elderly, for instance by increasing the choice of available interaction modalities, will help ensure that the elderly have access to these technologies. Some previous research suggests that speech is the easiest and most natural modality for human-computer interaction (HCI) (Acartürk, 2015). Speech is also the preferred modality when interacting with mobile devices when users have permanent impairments such as arthritis, or when temporary limitations such as driving or carrying objects make it difficult to use other modalities like touch. It is hoped that ICT can be used to help maintain the health of the elderly. Daily verbal interaction helps them maintain their cognitive ability, reducing the risk of dementia. In a super-aging society such as Japan, where we face an acute shortage of care workers, spoken dialogue systems could play an important role. However, speech recognizers, which would need to be used in such interfaces and spoken dialogue systems, do not yet work well for elderly users. A mismatch between the acoustic model and the acoustic characteristics of user speech is one …

Content truncated to 500 words