2014 · 13 citations · 16 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingConversational User InterfacesDialogue SystemsLanguage ModelingLanguage ModelsSpeech RecognitionSpoken CorporaDialog SystemsDomain-specific Language EngineeringDomain-specific ModelingLanguage Model PretrainingSpeech Recognition AccuracySpeech Recognition EvaluationSpeech UnderstandingTelephony Systems
In this paper, we investigate whether the open-source speech recognizer Sphinx can be tuned to outperform Google’s cloud-based speech recognition API in a spoken dialog system task. According to this target domain, we use data from CMU’s Let’s Go bus information system comprising 258k utterances of telephony speech recorded in the bus information dialog system of Pittsburgh. By training a domain-specific language model on the aforementioned corpus and tuning a number of Sphinx’s parameters, we achieve a WER of 51.2%. This result is significantly lower than the one produced by Google’s speech recognition API whose language model is built on millions of times more training data.
16
Kaldi Speech Recognition Toolkit
Daniel Povey · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2024 · 4.9K citations · Full text
Computing, Linguistics, Acoustics +15
Building Watson: An Overview of the DeepQA Project
David Ferrucci, Eric W. Brown, Jennifer Chu‐Carroll et al. · AI Magazine · 2010 · 1.5K citations · Full text
Handbook of standards and resources for spoken language systems
Dafydd Gibbon, Roger K. Moore, Richard Winski · 1997 · 380 citations
Doing research on a deployed spoken dialogue system: one year of let's go! experience
Antoine Raux, Dan Bohus, Brian Langner et al. · 2006 · 136 citations