Hi All, Please join us tomorrow at the Change Seminar. Aditya Vashistha and Pooja Sethi will be talking about their project Respeak - which will be presented at CHI 2017 next week.
*What:* Respeak: A Voice-based, Crowed-powered Speech Transcription System *When: *Tuesday May 2 *Where: *12pm in CSE 203 *Abstract:* Speech transcription is an expensive service with high turnaround time for audio files containing languages spoken in developing countries and regional accents of well-represented languages. We present Respeak — a voice-based, crowd-powered, accessible speech transcription system that capitalizes on the strengths of crowdsourcing and automatic speech recognition (instead of typing) to transcribe such audio files. We created Respeak and optimized its design through a series of cognitive experiments. We deployed it with 25 university students in India who completed 5464 micro-transcription tasks transcribing widely-varied audio content with a word error rate of 10%, and collectively earning USD 46 as mobile airtime. Our findings suggest that Respeak improves the quality of speech transcription while enhancing the earning potential of low-income populations in resource-constrained settings. *Bio:* In this talk, Aditya Vashistha and Pooja Sethi will present Respeak. Aditya is a Computer Science PhD candidate and Pooja is a senior undergraduate Computer Engineering major at the Allen School.
_______________________________________________ change mailing list firstname.lastname@example.org http://changemm.cs.washington.edu/mailman/listinfo/change