Li Gong
ABSTRACT
Because it is impractical to record human voice for ever-changing dynamic content such as email messages and news, many commercial speech applications use human speech for fixed prompts and synthetic speech (TTS) for the dynamic content. However, this mixing approach may not be optimal from a consistency perspective. A 2-condition between-group experiment (N = 24) was conducted to compare two versions of a virtual-assistant interface (mixing human voice and TTS vs. TTS-only). Users interacted with the virtual assistant to manage some email and calendar tasks. Their task performance, self-perception of task performance, and attitudinal responses were measured. Users interacting with the TTS-only interface performed the task significantly better, while users interacting with the mixed-voices interface thought they did better and had more positive attitudinal responses. Explanations and design implications are suggested.
- 1.Domangue, B.B. Decoding effects of cognitive complexity, tolerance of ambiguity, and verbalnonverbal inconsistency. Journal of Personality, 46, 519-535, 1978.Google Scholar
Cross Ref
- 2.Fiske, S.T. and Taylor, S.E. Social Cognition. New York: McGraw-Hill, 1991.Google Scholar
- 3.Graves, J.R. and Robinson, J.D. Proxemic behavior as a function of inconsistent verbal and nonverbal messages. Journal of Counseling Psychology, 23, 333-338, 1976.Google ScholarCross Ref
- 4.Hendrick, C. Effects of salience of stimulus inconsistency on impression formation. Journal of Personality & Social Psychology, 22, 219-222, 1972.Google Scholar
- 5.Isbister, K. and Nass, C. Consistency of personality in interactive characters: Verbal cues, non-verbal cues, and user characteristics. International Journal of Human- Computer Studies, 53, 251-267, 2000. Google ScholarDigital Library
- 6.Kelley, H. H. Attribution theory in social psychology. In D. Levine (Ed.), Nebraska Symposium on Motivation (Vol. 15, pp. 192-240). Lincoln: University of Nebraska Press, 1967.Google Scholar
- 7.Lai, J., Wood, D., and Considine, M. The effect of task conditions on the comprehensibility of synthetic speech. The Proceedings of CHI '00 (The Hague, The Netherlands, March 2000), ACM Press, 321-328. Google ScholarDigital Library
- 8.Nass, C. and Gong, L. Maximized modality or constrained consistency? The Proceedings of AVSP'99 (Santa Cruz CA, August 1999), 1-5.Google Scholar
- 9.Olive, J.P. "The talking computer": Text-to-speech synthesis. In Stork D.G. (Ed.), HAL's Legacy: 2001's Computer as Dream and Reality (pp. 101-131). Cambridge, MA: MIT Press, 1997.Google Scholar
- 10.Ralston, J.V., Pisoni, D.B., and Mullennix, J.W. Perception and comprehension of speech. In Syrdal, A.K., Bennett, R.W., Greenspan, S.L. (Eds.), Applied Speech Technology (pp. 233-288). Boca Raton: CRC Press, 1995.Google Scholar
- 11.Reeves, B. and Nass, C. The Media Equation: How People Treat Computers, Television, and New Media like Real People and Places. New York: Cambridge University Press/CSLI, 1996. Google ScholarDigital Library
- 12.www.conita.comGoogle Scholar
- 13.www.genmagic.com/portico/portico_home.shtmlGoogle Scholar
- 14.www.lhsl.com/realspeak/demo.cfmGoogle Scholar
- 15.www.research.att.com/projects/ttsGoogle Scholar
Index Terms
- Shall we mix synthetic speech and human speech?: impact on users' performance, perception, and attitude
Recommendations
Intelligibility of time-compressed synthetic speech
Analysis of listeners' intelligibility of natural and synthetic time-compressed speech.Different compression methods are applied to normal and fast speech.We evaluated a linear method and two non linear methods that act on the duration model.The linear ...
Speech-Input Speech-Output Communication for Dysarthric Speakers Using HMM-Based Speech Recognition and Adaptive Synthesis System
Dysarthria is a motor speech disorder that causes inability to control and coordinate one or more articulators. This makes it difficult for a dysarthric speaker to utter certain speech sound units, thereby producing poorly articulated, slurred, and ...
Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach
Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often ...
Comments