tailieunhanh - Báo cáo khoa học: "Vocabulary Decomposition for Estonian Open Vocabulary Speech Recognition"

Speech recognition in many morphologically rich languages suffers from a very high out-of-vocabulary (OOV) ratio. Earlier work has shown that vocabulary decomposition methods can practically solve this problem for a subset of these languages. This paper compares various vocabulary decomposition approaches to open vocabulary speech recognition, using Estonian speech recognition as a benchmark. Comparisons are performed utilizing large models of 60000 lexical items and smaller vocabularies of 5000 items. . | Vocabulary Decomposition for Estonian Open Vocabulary Speech Recognition Antti Puurula and Mikko Kurimo Adaptive Informatics Research Centre Helsinki University of Technology 5400 FIN-02015 HUT Finland puurula mikkok @ Abstract Speech recognition in many morphologically rich languages suffers from a very high out-of-vocabulary OOV ratio. Earlier work has shown that vocabulary decomposition methods can practically solve this problem for a subset of these languages. This paper compares various vocabulary decomposition approaches to open vocabulary speech recognition using Estonian speech recognition as a benchmark. Comparisons are performed utilizing large models of 60000 lexical items and smaller vocabularies of 5000 items. A large vocabulary model based on a manually constructed morphological tagger is shown to give the lowest word error rate while the unsupervised morphology discovery method Morfessor Baseline gives marginally weaker results. Only the Morfessor-based approach is shown to adequately scale to smaller vocabulary sizes. 1 Introduction OOV problem Open vocabulary speech recognition refers to automatic speech recognition ASR of continuous speech or speech-to-text of spoken language where the recognizer is expected to recognize any word spoken in that language. This capability is a recent development in ASR and is required or beneficial in many of the current applications of ASR technology. Moreover large vocabulary speech recogni-89 tion is not possible in most languages of the world without first developing the tools needed for open vocabulary speech recognition. This is due to a fundamental obstacle in current ASR called the out-ofvocabulary OOV problem. The OOV problem refers to the existence of words encountered that a speech recognizer is unable to recognize as they are not covered in the vocabulary. The OOV problem is caused by three intertwined issues. Firstly the language model training data and the test data always come .