Word error rate

About: Word error rate is a research topic. Over the lifetime, 11939 publications have been published within this topic receiving 298031 citations.

Phonetic Speaker Recognition with Support Vector Machines

Abstract: A recent area of significant progress in speaker recognition is the use of high level features—idiolect, phonetic relations, prosody, discourse structure, etc. A speaker not only has a distinctive acoustic sound but uses language in a characteristic manner. Large corpora of speech data available in recent years allow experimentation with long term statistics of phone patterns, word patterns, etc. of an individual. We propose the use of support vector machines and term frequency analysis of phone sequences to model a given speaker. To this end, we explore techniques for text categorization applied to the problem. We derive a new kernel based upon a linearization of likelihood ratio scoring. We introduce a new phone-based SVM speaker recognition approach that halves the error rate of conventional phone-based approaches.

Maximum Entropy Based Restoration of Arabic Diacritics

Abstract: Short vowels and other diacritics are not part of written Arabic scripts. Exceptions are made for important political and religious texts and in scripts for beginning students of Arabic. Script without diacritics have considerable ambiguity because many words with different diacritic patterns appear identical in a diacritic-less setting. We propose in this paper a maximum entropy approach for restoring diacritics in a document. The approach can easily integrate and make effective use of diverse types of information; the model we propose integrates a wide array of lexical, segment-based and part-of-speech tag features. The combination of these feature types leads to a state-of-the-art diacritization model. Using a publicly available corpus (LDC's Arabic Treebank Part 3), we achieve a diacritic error rate of 5.1%, a segment error rate 8.5%, and a word error rate of 17.3%. In case-ending-less setting, we obtain a diacritic error rate of 2.2%, a segment error rate 4.0%, and a word error rate of 7.2%.

Speech recognition system having word-based and phoneme-based recognition means

Abstract: A speech recognition system includes a parameter extracting section for extracting a speech parameter of input speech, a first recognizing section for performing recognition processing by word-based matching, and a second recognizing section for performing word recognition by matching in units of word constituent elements. The first word recognizing section segments the speech parameter in units of words to extract a word speech pattern and performs word recognition by matching the word speech pattern with a predetermined word reference pattern. The second word recognizing section performs recognition in units of word constituent elements by using the extracted speech parameter and performs word recognition on the basis of candidates of an obtained word constituent element series. The speech recognition system further includes a recognition result output section for obtaining a recognition result on the basis of the word recognition results obtained by the first and second recognizing sections and outputting the obtained recognition result. The speech recognition system further includes a word reference pattern learning section for performing learning of a word reference pattern on the basis of the recognition result obtained by the recognizing result output section and the word speech pattern.

Multi-resolution RASTA filtering for TANDEM-based ASR

Abstract: New speech representation based on multiple filtering of temporal trajectories of speech energies in frequency sub-bands is proposed and tested. The technique extends earlier works on delta features and RASTA filtering by processing temporal trajectories by a bank of band-pass filters with varying resolutions. In initial tests on OGI Digits database the technique yields about 30% relative improvement in word error rate over the conventional PLP features. Since the applied filters have zero-mean impulse responses, the technique is inherently robust to linear distortions.

Word Sense Disambiguation vs. Statistical Machine Translation

Abstract: We directly investigate a subject of much recent debate: do word sense disambiguation models help statistical machine translation quality? We present empirical results casting doubt on this common, but unproved, assumption Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone Error analysis suggests several key factors behind this surprising finding, including inherent limitations of current statistical MT architectures