Using redundant speech and handwriting for learning new vocabulary and understanding abbreviations

New language constantly emerges from complex, collaborative human-human interactions like meetings -- such as, for instance, when a presenter handwrites a new term on a whiteboard while saying it. Fixed vocabulary recognizers fail on such new terms, which often are critical to dialogue understanding. We present a proof-of-concept multimodal system that combines information from handwriting and speech recognition to learn the spelling, pronunciation and semantics of out-of-vocabulary terms from single instances of redundant multimodal presentation (e.g. saying a term while handwriting it). For the task of recognizing the spelling and semantics of abbreviated Gantt chart labels across a held-out test series of five scheduling meetings we show a significant relative error rate reduction of 37% when our learning methods are used and allowed to persist across the meeting series, as opposed to when they are not used.