论文信息 - Speech dasher: fast writing using speech and gaze

Speech dasher: fast writing using speech and gaze

Speech Dasher allows writing using a combination of speech and a zooming interface. Users first speak what they want to write and then they navigate through the space of recognition hypotheses to correct any errors. Speech Dasher's model combines information from a speech recognizer, from the user, and from a letter-based language model. This allows fast writing of anything predicted by the recognizer while also providing seamless fallback to letter-by-letter spelling for words not in the recognizer's predictions. In a formative user study, expert users wrote at 40 (corrected) words per minute. They did this despite a recognition word error rate of 22%. Furthermore, they did this using only speech and the direction of their gaze (obtained via an eye tracker).

Keith Vertanen | David J. C. MacKay | K. Vertanen | D. Mackay | D. MacKay

[1] Daniel B. Horn,et al. Patterns of entry and correction in large vocabulary continuous speech recognition systems , 1999, CHI '99.

[2] Alan F. Blackwell,et al. Dasher—a data entry interface using continuous gestures and language models , 2000, UIST '00.

[3] Sharon L. Oviatt,et al. Taming recognition errors with a multimodal interface , 2000, CACM.

[4] Alexander H. Waibel,et al. Multimodal error correction for speech user interfaces , 2001, TCHI.

[5] David J. Ward,et al. Fast Hands-free Writing by Gaze Direction , 2002, ArXiv.

[6] Kevin Larson,et al. Speech Error Correction: The Story of the Alternates List , 2003, Int. J. Speech Technol..

[7] Alexander I. Rudnicky,et al. Pocketsphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.