Abstract
For the purpose of language retrieval for English listening, this paper designs and implements a cross-language information retrieval system for English listening. Different implementation methods of cross-language information retrieval, query, and translation are analyzed. The system adopts cross-language information retrieval technology based on bilingual dictionaries. According to the cross-language retrieval system of the existing bilingual dictionaries and monolingual dictionaries, based on the design and implementation of the fuzzy search dictionary lookup mechanism, the existing dictionary lookup mechanism is constructed and analyzed. Aiming at the problem of translation ambiguity in information retrieval systems based on bilingual dictionaries, a disambiguities elimination algorithm based on cooccurrence technology is proposed. In continuous speech, the speed of different speakers in different contexts is very different. Deviation from normal speech speed often leads to recognition errors, which makes recognition performance decline. Considering that the influence of speech speed on the length of speech units increases or decreases synchronously, and there is a strong correlation between the lengths of adjacent speech units, an adaptive speech speed algorithm is proposed based on the framework of implicit Markov model based on the information of the length of speech units. Experiments on number string and large vocabulary continuous speech recognition show that the algorithm is effective.
Highlights
IntroductionThe speed of speech of different speakers in different contexts is very different
In continuous speech, the speed of speech of different speakers in different contexts is very different
An adaptive speech speed adjustment algorithm is introduced to detect phonemic attributes. e algorithm takes sentence as unit and uses continuously changing frame length and frame shift interval to normalize the speech speed, so that the adjusted speech speed is consistent with the average speech speed of corpus
Summary
The speed of speech of different speakers in different contexts is very different. In a short period of time, a speaker’s speaking speed will be relatively stable; that is, the influence of such speed on the length of a paragraph can be considered to be basically the same In this way, the deviation of the previous segment length from its mean value can be used to predict the changing trend of the later segment length. If the speech speed deviating from the training data is too fast or too slow, there will be a large mismatch between the corresponding segment length and the segment length information trained by the training corpus, which will degrade the recognition performance. When each segment is compressed relative to a phoneme or syllable in the time domain, the longer the speech segment is, the more stable the characteristics are and the more similar the waveform is, so it can be compressed to a greater extent without losing too much information.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
