12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Visual Voice Mail to Text on the iPhone/iPad

Andrej Ljolje, Vincent Goffin, Diamantino Caseiro, Taniya Mishra, Mazin Gilbert

AT&T Labs Research, USA

Our visual Voice-Mail-to-Text (VMTT) transcription system takes a conventional voice mail and converts it to formatted text following standard punctuation, capitalization and presentation conven- tions. The text can then be used in a plethora of applications, from emails, to databases, text messages etc., which in turn allow searching, classification, data extraction, statistical analyses and other processes. Here we demonstrate our fully automated VMTT application by displaying the best scoring hypotheses from various recognition passes, the addition of punctuation and capitalization, formatting by using appropriate conventions for times, dates, dollar amounts and abbreviations, and finally applying grayscaling to lower the impact of the words recognized with low confidence scores.

Full Paper

Bibliographic reference.  Ljolje, Andrej / Goffin, Vincent / Caseiro, Diamantino / Mishra, Taniya / Gilbert, Mazin (2011): "Visual voice mail to text on the iphone/ipad", In INTERSPEECH-2011, 3337-3338.