Voice fuzzy retrieval method and apparatus
A fuzzy, phonetic technology, applied in the field of speech recognition and retrieval, can solve problems such as inaccurate retrieval, achieve fast and accurate retrieval, and overcome adverse effects
Active Publication Date: 2010-08-11
TSINGHUA UNIV +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention provides a speech fuzzy retrieval method and device to solve the problem of inaccurate retrieval existing in the existing speech recognition technology
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] The voice fuzzy retrieval scheme provided by the present invention adds a suitable language model to improve the accuracy rate during recognition, performs character string fuzzy matching when using the recognition result as text retrieval to reduce the impact of recognition errors, and calculates candidate keywords as The posterior probability of audio content is verified, thereby greatly improving the accuracy and reliability of retrieval.
[0039] Referring to Fig. 1, it is the speech fuzzy retrieval method flowchart of the present invention, comprises the following steps:
[0040] S101: Perform speech recognition on the acquired speech signal by using a preset acoustic model and language model, and obtain a recognition result;
[0041] S102: Use the preset index table to search in the preset text item library according to the recognition result to obtain the primary selection item;
[0042] Wherein, the preset text entry library is generally a massive text entry li...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method and a device which are used for speech fuzzy retrieval, wherein, the method comprises the following steps: speech recognition is performed on the obtained speech signals by utilizing a preset acoustic model and a language model, and recognition results are obtained; retrieval is performed in a preset text entry database by utilizing a preset index table according to the recognition results, and primarily elected entries are obtained; fuzzy matching for character strings is performed between the primarily elected entries and the recognition results, entries of which the matching degree is in a threshold value range of preset matching degree are selected as well-chosen entries, and meanwhile, the matching position of each entry is recorded; posterior probability between the text of the matching part and the well-chosen entries and voice signals are calculated; and finally, a plurality of entries are selected as the retrieval results of voice signals by utilizing the posterior probability and the matching proportion obtained through the matching positions. By adopting the invention, text entries matched with the voice signals can be retrieved quickly and accurately in a great capacity text entry database on the basis of voice signals.
Description
technical field [0001] The invention relates to the fields of speech recognition and retrieval, in particular to a speech fuzzy retrieval method and device. Background technique [0002] As a branch of multimedia retrieval technology, speech fuzzy retrieval is different from traditional text retrieval and audio retrieval. Retrieval, that is, how to retrieve text information related to its content in the text library according to a piece of voice signal submitted by the user. [0003] Speech recognition technology can convert speech signals into text content. If the converted text is used and the text retrieval method is used for reference, the retrieval of audio from the text library can be realized. However, speech recognition technology cannot be 100% accurate, especially for spoken language For speech, the recognition accuracy rate is usually lower than 90%. It is conceivable that if non-accurate text is used to retrieve a massive text entry library, the retrieval result...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30G10L15/00G10L15/08
Inventor 王智国吴及钱胜吕萍陈志刚胡国平胡郁刘庆峰吴晓如王仁华
Owner TSINGHUA UNIV