International Joint Conference on Natural Language Processing · 2017 · 20 citations · 17 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingLanguage ModelsNatural Language UnderstandingParsingSpeech RecognitionNatural Language InferenceNatural Language InterfacesRecognition ErrorsSpeech Understanding
Speech is a natural channel for human-computer interaction in robotics and consumer applications. Natural language understanding pipelines that start with speech can have trouble recovering from speech recognition errors. Black-box automatic speech recognition (ASR) systems, built for general purpose use, are unable to take advantage of in-domain language models that could otherwise ameliorate these errors. In this work, we present a method for re-ranking black-box ASR hypotheses using an in-domain language model and semantic parser trained for a particular task. Our re-ranking method significantly improves both transcription accuracy and semantic understanding over a state-of-the-art ASR’s vanilla output.
17
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations
Applied Physics Letters · 2000 · 1.8K citations · Full text
Achieving Human Parity in Conversational Speech Recognition
Wayne Xiong, Jasha Droppo, Xuedong Huang et al. · arXiv (Cornell University) · 2016 · 479 citations · Full text