New methods for the analysis of repeated utterances
Geoffrey Zweig · 2009
This paper proposes three novel and effective procedures for jointly analyzing repeated utterances. First, we propose repetition-driven system switching, where repetition triggers the use of an independent backup system for decoding. Sec-ond, we propose a cache language model for use with the sec-ond utterance. Finally, we propose a method with which the acoustics from multiple utterances- not necessarily exact repe-titions of each other- can be combined to into a composite that increases accuracy. The combination of all methods produces a relative increase in sentence accuracy of 65.7 % for repeated voice-search queries. Index Terms: speech recognition, joint decoding, repeated ut-terances