Progress and Prospects for Spoken Language Technology: What Ordinary People Think

Abstract

Arguably the most significant milestone (so far) in the spoken language technology field was the appearance in November 2011 of Siri-Apple's voice-based 'personal assistant and knowledge navigator' for the iPhone. Siri brought the potential of spoken language technology to the attention of the wider general public, and speech finally became "mainstream". This meant that ordinary people suddenly had an informed opinion about the merits (or otherwise) of using their voice to access information, send messages and control their smart devices. So, this paper presents the results of two surveys that were conducted in order to find out what ordinary people think about contemporary spoken language technology. The first used a modified version of the surveys conducted every six years at the IEEE ASRU series of workshops, and the second addressed questions about the awareness and usage of speech technology by members of the general public. The overall results suggest that ordinary people are more optimistic than the experts about what spoken language technology might have to offer, but usage patterns reveal that the majority of end users still prefer typing to talking, with accuracy, privacy and online accessibility cited as the main impediments to wider take-up.

Mapping Perceptions of Humanness in Intelligent Personal Assistant Interaction

“…Research [15,16,20,38,40,44] has consistently identified that humanness is fundamental to speech interface design, supporting the metaphor of human dialogue for interaction. It is currently unclear what dimensions are important in users' conceptualisation of humanness and how people see speech interface functionality through this lens.…”

“…This humanness seems to give users expectations as to the type of capabilities that a system may have as a dialogue partner [36,38]. Indeed, incongruence between expectations derived from humanness cues and the realities of interacting with speech-based systems is detrimental to speech interface user experience [17,38,40,45]. Qualitative work investigating the user experience of speech-based IPAs for both power users [38] and infrequent users [17], found that they seem to initially use human dialogue as a metaphor for interaction.…”

“…This work suggests that users tend to use human dialogue as an initial interaction metaphor, with expectations of system competence and function being set by the human-likeness of their design [15,17,38]. Emulating aspects of humanness in speech interfaces is common [8,10,16,37], although the wisdom of this design choice has been questioned [10,12,17,40] as it may create unrealistic expectations of system capability [38]. That said, currently it is not clear how people conceptualise the humanness of speechbased IPAs and how exactly users perceive that humans and speech interfaces vary when considering humanness as the metaphor for interaction.…”

User interactions with “Alexa” in public academic space

“…Cowan et al's (2017) study of infrequent Siri users revealed that the lack of trust in IPA abilities and poor quality of the voice-controlled interface contribute to technology non-use. Similarly, a survey of IPA users by Moore et al (2016) found a link between poor speech recognition accuracy and a decrease in usage.…”

Toward a Needs-Based Architecture for ‘Intelligent’ Communicative Agents: Speaking with Intention

“…Not only can real-world conditions (such as noisy environments, strong accents, older/younger users or nonnative speakers) lead to very poor speech recognition accuracy, but the 'understanding' exhibited by contemporary systems is rather shallow. As a result, after initial enthusiasm, users often lose interest in talking to Siri or Alexa, and they revert to more traditional interface technologies for completing their tasks (Moore et al, 2016).…”