Loading…
NEW THIS YEAR! The schedule of technical sessions is in Sched.org which allows you to search within the schedule, filter the schedule to show sessions only occurring on a certain date, within a track, or in a room. You can also build your own schedule by creating a free account in Sched.org. Click here to return to the main Midwest Fish & Wildlife Conference website. 

PLEASE NOTE: The schedule posted here is as of 1/25/16, and is subject to change. Please check back for updates.
Back To Schedule
Wednesday, January 27 • 2:00pm - 2:20pm
Application of Voice Recognition Software For Fish Biological Data Collection

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

AUTHORS: Daniel J. Traynor*, Michigan Department of Natural Resources; Shawn P. Sitar, Michigan Department of Natural Resources

ABSTRACT: Traditional fish biological data collection involves about six steps until data are ready for analyses. These steps include: observation, relay, recording, transcription to database, data proofing, and error correction. The traditional data collection process requires at least two people: an observer that speeches data to the data recorder. The recording medium in the field has typically paper data sheets and has evolved to electronic entry on portable computers. Data that are recorded on paper are entered into computer databases and are prone to keypunch errors. Quality control measures to detect and correct errors from keypunched data are time consuming and costly. Electronic entry of fish biodata in the field eliminates the data transcription step, but can be slow and inefficient when high numbers of fish must be sampled. In order to make fish biodata collection more efficient and to reduce errors, we utilized desktop voice recognition software integrated with a relational computer database to develop the Voice Data Recording System for use on our research vessel for fish surveys on Lake Superior. The hardware includes laptop computer, wireless headset, computer monitor, and label printer. A portable version of the VDRS system for monitoring commercial fisheries landings includes only a laptop computer and wireless headset. The VDRS has been used since 2009 processing over 33,000 fish with more than 620,000 measurements and making our research vessel paperless. Furthermore, the VDRS has been able to successfully record fish biodata under high noise and high sea conditions. The VDRS has saved our station about 150-200 staff hours per year because many of the traditional data collection steps have been eliminated. Our successful use of voice recognition technology to efficiently record fish biological data onboard a research vessel and in commercial harvest monitoring indicates potential applicability to other types of fish surveys.

Wednesday January 27, 2016 2:00pm - 2:20pm EST
Gerald Ford