Spoken2Sign

Spoken Language ->> Sign Language Translation

[1] The iCommunicator translates in real-time: Speech to Text, Speech/Text to Video Sign-Language, and Speech/Text to Computer Generated Voice.

Comments: The text to speech part seems fine. An indication that they might not quite understand their end-users: "The iCommunicator delivers American Sign Language (ASL) signs in English word order (subject+verb+object) to improve the association between spoken, written, and signed words, promoting better literacy levels than traditional ASL."

Signing Avatars:

[2] Matt Huenerfauth. American Sign Language Natural Language Generation and Machine Translation. ACM SIGACCESS Accessibility and Computing 2005. New York: ACM Press. Issue 81.

[3] Beifang Yi, Frederick C. Harris, Jr., Sergiu M. Dascalu. From Creating Virtual Gestures to Writing in Sign Languages. ACM CHI 2005. pages 1885-1888.

[4] Cox, S., Lincoln, M., Tryggvason, J., Nakisa, M., Wells, M., Tutt, M., and Abbott, S. 2002. Tessa, a system to aid communication with deaf people. ASSETS 2002. ACM Press, New York, NY, 205-212.

Comments: TESSA aids in the communication between a deaf person and a clerk at a Post Office, converting the clerk's voice (using pre-trained voice rec. software) into BSL on a screen using a signing avatar (with only a constrained set of words in post office context). Intelligibility and Acceptability rates are not impressive, but TESSA does appear to decrease total communication time. No reverse communication (from deaf person to clerk).

[5] Liwei Zhao, Karin Kipper, William Schuler, Christian Vogler, Norm Badler, and Martha Palmer. A Machine Translation System from English to American Sign Language. Proceedings of the Association for Machine Translation in the Americas 2000, Published in Lecture Notes in AI series of Springer-Verlag, pages 54-67.

Kazunari Morimoto, Takao Kurokawa, Syouhei Kawamura. Improvements and Evaluations in Sign Animation Used as Instructions for Stomach X-Ray Examination. ICCHP 2006: 607-614

Comments: Very obscure and constrained domain.

[6] Chuanjun Li and B. Prabhakaran. A Similarity Measure for Motion Stream Segmentation and Recognition. Proceedings of the 6th international workshop on Multimedia data mining: mining integrated media and complex data 2005, pages 89-94.

Comments: Used a CyberGlove to recognize and reproduce specific motions (gestures).

[7] Vcom3D. SigningAvatar.

Comments: This is software that seems to translate English text into signs. An avatar does the signing in a smooth way.

Toro, J., and et al. A graphical environment for transcription of american sign language. Information 4 (2001), 533–539.

Comments: This is a transcription system that allows users to select hand shapes and hand positions; the system then interpolates between them to produce a sentence in sign language. Only 40 hand shapes make up signs, seems like a useful fact.