Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing

Johannes Twiefel, Timo Baumann, Stefan Heinrich, Stefan Wermter

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

Automatic speech recognition (ASR) technology has been developed to such a level that off-the-shelf distributed speech recognition services are available (free of cost), which allow researchers to integrate speech into their applications with little development effort or expert knowledge leading to better results compared with previously used open-source tools. Often, however, such services do not accept language models or grammars but process free speech from any domain. While results are very good given the enormous size of the search space, results frequently contain out-of-domain words or constructs that cannot be understood by subsequent domain-dependent natural language understanding (NLU) components. We present a versatile post-processing technique based on phonetic distance that integrates domain knowledge with open-domain ASR results, leading to improved ASR performance. Notably, our technique is able to make use of domain restrictions using various degrees of domain knowledge, ranging from pure vocabulary restrictions via grammars or N-Grams to restrictions of the acceptable utterances. We present results for a variety of corpora (mainly from human-robot interaction) where our combined approach significantly outperforms Google ASR as well as a plain open-source ASR solution.
Original languageEnglish
Title of host publicationProceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI-14)
EditorsCarla E. Brodley, Peter Stone
Number of pages7
PublisherAAAI Press
Publication date1 Jul 2014
Pages1529-1535
DOIs
Publication statusPublished - 1 Jul 2014
Externally publishedYes

Fingerprint

Dive into the research topics of 'Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing'. Together they form a unique fingerprint.

Cite this