Lessons from Project LISTEN: What Have We Learned from a Reading Tutor That Listens?
نویسنده
چکیده
For 20+ years, Project LISTEN (www.cs.cmu.edu/~listen) has made computers listen to children read aloud, and help them learn to read. Along the way we have learned lessons about children, reading, speech technology, intelligent tutors, educational data mining, and doing AIED research in schools. 1 Some of the Research Questions Project LISTEN Has Studied Nobel laureate Herbert Simon’s annual talk on how to do research advised incoming PhD students to pick research questions (not merely topics) both significant (i.e., that people care about) and right-sized (not too hard). Questions we have studied include: What ought a Reading Tutor do? AAAI94*, CALICO 99, ICMI02, STLL 08 Do children like a feature? AIED05, SLaTE11 Which system features matter? SIGDial11 What should the Reading Tutor listen for, why, and how? Eurospeech93&03, ESCA99, HMC00, AAAI94*, ICSLP98&02&06, AIED01&05&07, ICAAI03, EDM08, Interspeech09&11, SLaTE09&11, ITS10, TSLP 11, FLAIRS12, Chen 12, ISADEPT12, IJAIED 13 How much is it used, and why? Kant 04, IERI 07 Do Reading Tutor gains beat... classroom instruction? ETS 02, STLL 08 human tutors? JECR 03 independent reading? JECR 07 ELL instruction in ... Canada? IDEC07&09; Ghana? ITID 10; India? Dev10 How to model word meaning? SSSR09, EACL12 How to generate... questions? Aist 01*, AIED03, QG09&11, BEA12 examples? BEA11, JNLE 12 instruction? AAAI99, IJAIED 01, ITS04&06, AIED09 How to model students? ITS02&04&06&08*, UM03&07, TICL 04, AIED05&07, IJAIED 06, EDM07&08&10&11&12*, ICWS09, LSA10, TSLP 11 What practice helps most? FF 01, FLET 08, ITS08*, SSSR12 Could EEG help? AIED11*, Tan 12, NAACL12 How to mine student data? JNLE 06, ITS06, HEDM 10, EDM10&11, FLAIRS12* 1 www.cs.cmu.edu/~listen lists articles, chapters, conferences, theses, and awards*.
منابع مشابه
Why and How Our Automated Reading Tutor Listens
Project LISTEN’s Reading Tutor listens to children read aloud, and helps them learn to read. This paper outlines how it gives feedback, how it uses ASR, and how we measure its accuracy. It describes how we model various aspects of oral reading, some ideas we tried, and lessons we have learned about acoustic models, lexical models, confidence scores, language models, alignment methods, and proso...
متن کاملWhy, What, and How to Log? Lessons from LISTEN
There is presumably unanimous consensus in the EDM community that it is useful to log tutor data. However, there is far from a consensus about which data to log, or how. As a step toward this goal, this paper attempts to distill lessons from over fifteen years of experience in logging and mining data from Project LISTEN’s Reading Tutor [1] and its predecessor [2]. We cite relevant publications ...
متن کاملA Prototype Reading Coach that Listens: Summary of Project LISTEN
What: Project LISTEN is developing a novel weapon against illiteracy: an automated reading coach that displays a story on a computer screen, listens to a child read it aloud, and helps where 1. needed. The coach provides a combination of reading and listening, in which the child reads wherever possible, and the coach helps wherever necessary. We demonstrated a prototype of this coach at the ARP...
متن کاملWhen Listening is Not Enough: Potential Uses of Vision for a Reading Tutor that Listens
Speech offers a powerful avenue between user and computer. However, if the user is not speaking, or is speaking to someone lse, what is the computer to make of it? Project LISTEN’s Reading Tutor is speech-aware software that strives to teach children to read. Because it is useful to know what the child is doing when reading, we are investigating some potential uses of computer vision. By record...
متن کاملAdding Human-Provided Emotional Scaffolding to an Automated Reading Tutor That Listens Increases Student Persistence
1 With Project LISTEN 1996-2001; now Visiting Scientist, MIT M edia Lab; and Research Scientist, Research Institute for Advanced Computer Science, Mail Stop T27-A, NASA Ames Research Center, Moffett Field CA 94035-1000 USA [email protected] 2 MIT Media Lab, Building E15, 77 Massachusetts Ave., Cambridge MA 02139 USA http://affect.media.mit.edu/AC_research/lc/ 3 Project LISTEN, RI-NSH 4213, ...
متن کامل