Finding consensus among words: lattice-based word error minimization
نویسندگان
چکیده
We describe a new algorithm for finding the hypothesis in a recognition lattice that is expected to minimize the word error rate (WER). Our approach thus overcomes the mismatch between the word-based performance metric and the standard MAP scoring paradigm that is sentence-based, and that can lead to sub-optimal recognition results. To this end we first find a complete alignment of all words in the recognition lattice, identifying mutually supporting and competing word hypotheses. Finally, a new sentence hypothesis is formed by concatenating the words with maximal posterior probabilities. Experimentally, this approach leads to a significant WER reduction in a large vocabulary recognition task.
منابع مشابه
Finding consensus in speech recognition: word error minimization and other applications of confusion networks
We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach the recognizer outputs the string of words corresponding to the path with the highest posterior probability given the acoustics and a language model. However,...
متن کاملLattice-Based Risk Minimization Training for Unsupervised Language Model Adaptation
This paper describes a lattice-based risk minimization training method for unsupervised language model (LM) adaptation. In a broadcast archiving system, unsupervised LM adaptation using transcriptions generated by speech recognition is considered to be useful for improving the performance. However, conventional linear interpolation methods occasionally degrade the performance because of incorre...
متن کاملDiscriminative rescoring based on minimization of word errors for transcribing broadcast news
This paper describes a novel method of rescoring that reflects tendencies of errors in word hypotheses in speech recognition for transcribing broadcast news, including ill-trained spontaneous speech. The proposed rescoring assigns penalties to sentence hypotheses according to the recognition error tendencies in the training lattices themselves using a set of weighting factors for feature functi...
متن کاملAn Efficient OCR Error Correction Method for Japanese Text Recognition
OCR error correction using Japanese morphological analysis contains two time-consuming procedures: extraction of candidate words from combinations of candidate characters, and finding the most plausible word sequence in combinations of the candidate words. In this paper an optimal word extraction technique, and the use of lexical entries that are tailored for Japanese verb inflection, are inves...
متن کاملLattice extension and rescoring based approaches for LVCSR of Turkish
In this paper, we present some techniques to solve the problems of Turkish Large Vocabulary Continuous Speech Recognition (LVCSR). Its agglutinative nature makes Turkish a challenging language in terms of speech recognition since it is impossible to include all possible words in the recognition lexicon. Therefore, data-driven sub-word recognition units, in addition to words, are used in a newsp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999