![]() ![]() The task is divided into two stages: text error detection and text error correction. In this paper, a text processing model after Chinese Speech Recognition is proposed, which combines a bidirectional long short-term memory (LSTM) network with a conditional random field (CRF) model. After the general speech recognition technology, the text after speech recognition can be detected and corrected in the specific context, which is helpful to improve the robustness of text comprehension and is a beneficial supplement to the speech recognition technology. In the process of speech-to-text conversion, due to the influence of dialect, environmental noise, and context, the accuracy of speech-to-text in multi-round dialogues and specific contexts is still not high. Chinese Speech Recognition is a complex process. With the rapid development of Internet of Things Technology, speech recognition has been applied more and more widely. Since the recall of Levenshtein is higher than N-gram, it is concluded that the frequency of misspelling words which are correctly fixed by Levenshteinoccurs more often. This study aims to identify the common type of spelling error and it uses the list of common misspelling words submitted by Wikipedia contributors.A brief overview of Levenshtein and N-gram distance techniques is provided to describe the technical approaches that support the author to achieve the purpose of this study.Those two techniques are utilised to predict the correct word of misspellings from the English dictionary.This study shows that Levenshtein works well to correct substitution single letter and transposition two sequenced letters, while N-gram operates effectively to fix the word with letter omission.The overall result is then evaluated by recall measurement to see which technique that works well on correcting the misspellings. The types of errors that mostly appear such as insertion of an extra letter, deletion of one letter, substitution of one letter, or transposition of two adjacent letters. It probably happens due to the authors’ vocabulary incompetence or they may strike the improper key in the keyboard. A spelling error commonly occurs during document writing.
0 Comments
Leave a Reply. |