@techreport{TD:100520,
	att_abstract={{People who are blind increasingly use synthesized speech as a primary output modality when interacting with computers, mobile devices, and web based services.They typically prefer to listen to the synthesized speech at speeds multiple times real time, and consequently develop strong preferences for particular text-to-speech (TTS) engines and voices. These usage based preferences lead to potentially incorrect assumptions about which TTS approaches are “best”for fast speech. We report on a cross-system comparison of the intelligibility of fast synthesized speech for users who are blind from birth. We used male and female voices from multiple TTS engines representing the main approaches to TTS: diphone synthesis, unit selection synthesis, HMM based synthesis,and formant synthesis. We recruited participants from organizations that work with the blind. Each participant listened to and transcribed semantically underspecified sentences from a single TTS engine and voice, spoken at speeds ranging from 300 to 550 words/min. We used TTS engine, algorithm for speeding up synthesized speech, and speaker sex as independent variables, and transcription accuracy as the primary dependent variable. We report differences by TTS approach,speed up method, TTS engine type, and speaker sex. }},
	att_authors={as791w, as9787, tm330a},
	att_categories={C_IIS.11},
	att_copyright={{}},
	att_copyright_notice={{}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={},
	att_techdoc={true},
	att_techdoc_key={TD:100520},
	att_url={http://web1.research.att.com:81/techdocs_downloads/TD:100520_DS1_2011-05-16T17:43:47.291Z.pdf},
	author={Amanda Stent and Ann Syrdal and Taniya Mishra},
	institution={{Acoustical Society of America}},
	month={May},
	title={{On the Intelligibility of Fast Synthesized Speech for People Who Are Blind: A
Cross-System Comparison}},
	year=2011,
}