Patent
Method and device for matching based on voice recognition
TLDR
In this paper, a method and a device for matching based on voice recognition is described, which mainly includes determining character information, in an alphabetic form, converted from voice information; on the basis of a fuzzy matching strategy and according to alphabet, performing fuzzy matching to the converted character information of the character information stored in the alphabetic and Chinese character forms from a local database.Abstract:
The invention discloses a method and a device for matching based on voice recognition. The method mainly includes determining character information, in an alphabetic form, converted from voice information; on the basis of a fuzzy matching strategy and according to alphabet, performing fuzzy matching to the converted character information of the character information stored in the alphabetic and Chinese character forms from a local database. As the single complete matching strategy applied in the prior art is expanded to the strategy of performing the fuzzy matching to the converted character information in the alphabetic form according to alphabet, voice recognition rate of the character information acquired by conversion is increased effectively, and further, the efficiency of the voice recognition technology is improved.read more
Citations
More filters
Patent
Voice wake-up method and voice interaction device
TL;DR: In this article, the authors presented a voice wake-up method and a voice interaction device, which includes the following steps that: voice input signals are received; the first similarity of the voice inputs signals and preset wake up voice signals is determined according to a first acoustic model, and whether the first similarities exceeds a first preset threshold value is judged; and if the second similarity between the speech input signals and the pre-wised voice signals was determined, if the two similarity exceeds the second preset threshold values, the voice interaction function was awaken, wherein the accuracy of the second acoustic model
Patent
Method and apparatus for speech recognition
TL;DR: In this article, a method and apparatus for speech recognition using Chinese-character-based and Chinese-phonetic-alphabet-based speech recognition is presented. But the method is not suitable for Chinese-to-English speech recognition.
Patent
Voice identification processing method and device
TL;DR: In this article, a voice identification method and a VIN device is described, which comprises steps of analyzing user key word in voice information of a user; detecting if the preset information base has user ID matched with the user key words; if not, obtaining spell character string corresponding to the users key word; according to the spell characters string, identifying at least one user ID which is similar with pronunciation of the speed character string from the preset Information base, and using the user ID as the result of voice identification processing.
Patent
Character string fuzzy matching method and apparatus
TL;DR: In this article, a character string fuzzy matching method was proposed, which consists of obtaining the number of matched characters of a source text and each target text, calculating the source matching degree of each source text according to the matched characters and the numbers of characters of the source text, and obtaining a first preset threshold value corresponding to the source texts according to their number of fields.
Patent
Method and system for broadcasting polyphonic characters in voice interaction process
TL;DR: In this paper, the authors proposed a method and a system for broadcasting polyphonic characters in the voice interaction process, which comprises the steps of acquiring voice information, and recognizing the voice information; forming feedback information; performing phonetic notation on the feedback information, broadcasting and releasing prior information.
References
More filters
Patent
Navigation method and system based on natural voice identification
TL;DR: In this paper, a navigation method and system based on natural voice identification is described, which relates to the field of communication, where the navigation result of the navigation destination address is acquired from a navigation server, and the result is displayed to the user.
Patent
Method for ordering song by voice
TL;DR: In this article, a data initialization module containing files of Chinese character database and a similarity metric value chart of initials and finals of Chinese syllables, a song database character pre-processing module containing character strings of target syllable chains corresponding to the name of the song or the names of the singer, and a voice recognition module for converting the voice recording data of the name-of-the-name input from the sound card into the corresponding character string of Chinese characters.
Patent
Sound identifying method for geographic information and its application in navigation system
Liang Zhang,Yi Long +1 more
TL;DR: In this paper, a speech recognition method of geographic data includes utilizing the existed speech recognition module and its calling interface to obtain recognized random character string and to convert it to be phonetic character string, calculating degree of matching for the two and using source string with most close degree of similarity as result character string i.e geographic data name.
Patent
Audio/video on demand method and system based on natural voice recognition
TL;DR: In this article, an audio/video on demand method and system based on natural voice recognition is described. But the authors focus on the field of communication and do not discuss the application of the system in the field in which the user can be connected to a network side through terminal equipment simply by pressing a key.