2010 · 19 citations · 6 references
ComputingComputer ScienceLinguisticsInformation RetrievalNatural Language ProcessingPhoneticsCorpus RetrievalLanguage ModelingSearch Log AnalysisSpeech InteractionSpeech RecognitionVoice ProcessingAutomated Data CollectionPhonetic SearchSearch Dialog SystemsSpeech Recognition SoftwareSpeech RetrievalUser ReviewsUser-generated Reviews
In this paper we describe our efforts to build a Mandarin Chinese voice search system. We describe our strategies for data collection, language, lexicon and acoustic modeling, as well as issues related to text normalization that are an integral part of building voice search systems. We show excellent performance on typical spoken search queries under a variety of accents and acoustic conditions. The system has been in operation since October 2009 and has received very positive user reviews.
6
Entropy-based Pruning of Backoff Language Models
Andreas Stolcke · ArXiv.org · 2000 · 267 citations · Full text
Building transcribed speech corpora quickly and cheaply for many languages
T. A. Hughes, Kaisuke Nakajima, Linne Ha et al. · 2010 · 76 citations