Getting closer: tailored human–computer speech dialog

Abstract

This paper presents an advanced call center, which adapts presentation and interaction strategy to properties of the caller such as age, gender, and emotional state. User studies on interactive voice response (IVR) systems have shown that these properties can be used effectively to ''tailor'' services to users or user groups who do not maintain personal preferences, e.g., because they do not use the service on a regular basis. The adopted approach to achieve individualization of services, without being able to personalize them, is based on the analysis of a caller's voice. This paper shows how this approach benefits service providers by being able to target entertainment and recommendation options. It also shows how this analysis at the same time benefits the customer, as it can increase accessibility of IVR systems to user segments which have particular expectations or which do not cope well with a ''one size fits all'' system. The paper summarizes the authors' current work on component technologies, such as emotion detection, age and gender recognition on telephony speech, and presents results of usability and acceptability tests as well as an architecture to integrate these technologies in future multi-modal contact centers. It is envisioned that these will eventually serve customers with an avatar representation of an agent and tailored interaction strategies, matching powerful output capabilities with advanced analysis of the user's input.

Age recognition for spoken dialogue systems: do we need it?

“…The greatest disadvantage of our approach is that compiling appropriate lexical frequency statistics takes time, whereas systems such as the one discussed by Metze et al [1] use voice features determined from the first response to adapt almost all aspects of the subsequent interaction, including products presented to the user. Although some of the word groups (please, hello) used are likely to occur in the first utterance or two, word groups…”

“…62% of all older users (n=16) and 4.2% of all younger users (n=1) used a Social interaction style. 1…”

“…Spoken dialogue systems (SDS) provide an invaluable source of information about user characteristics such as age, gender, and emotion: the user's speech. Detecting these characteristics from speech input allows systems to automatically adapt to user needs [1].…”

“…In this paper, we look at one particular instance of this paradigm: detection of older voices in order to adapt systems to the particular needs of older people. Older people potentially require the system to accommodate age-related changes in voice, speech, and cognition [1,2]. Other aspects that may be adapted to older people may include the products and services offered initially, the formality of system messages, and the level of politeness [1].…”

“…Older people potentially require the system to accommodate age-related changes in voice, speech, and cognition [1,2]. Other aspects that may be adapted to older people may include the products and services offered initially, the formality of system messages, and the level of politeness [1]. To complicate matters, older users are also more likely to be dissatisfied with badly designed systems or systems that cannot accommodate their particular interaction style [3,4,5].…”