Voice edition device, voice edition method, and voice edition program
By using pattern matching processing to edit voice data in a voice recognition device, the problem of complex and low-efficiency editing voice data operations on mobile terminals is solved, and the effects of editing voice data and expanding the recognition dictionary on mobile terminals are achieved conveniently and cheaply.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
no. 1 approach
[0117] FIG. 1 is a block diagram of a speech recognition device (which uses a speech editing device for speech recognition according to the present invention) according to an embodiment of the present invention.
[0118] The speech recognition device includes a sound analysis unit 10, a feature parameter extraction unit 12, a changed part specifying unit 14 (including a pattern matching unit 16 for specifying a changed part), a standard pattern generating unit 18, a standard pattern database updating unit 20, a pattern matching unit (speech recognition unit of speech recognition device for speech recognition) 22 and standard pattern database (speech recognition dictionary file) 24. The type of data stored in the standard pattern database 24 may be "feature parameter (cepstrum)", "speech converted into text form (dictionary data as character string)", or "speech data (waveform data)". In the following description, it is assumed that “feature parameters (cepstrum)” are stored as...
no. 2 approach
[0139] The second embodiment describes the structure and operation of a speech recognition device and a sequence for generating standard patterns. In this embodiment, various standard patterns are used to identify announcements broadcast in trains or subways.
[0140]For example, a commuter commuting by train or subway may miss the station (eg, Shibuya station) where he is supposed to get off. In this case, when a commuter passenger carries a mobile terminal equipped with a voice recognition device, the mobile terminal can recognize a notice "This station is Shibuya" broadcast in a train or subway, and activate vibration when it recognizes the notice device to remind commuters, thereby providing convenience. Therefore, commuter passengers can be prevented from forgetting to get off. In the case where commuters often get off at "Yokohama", the mobile terminal can be configured to activate the vibrator when it recognizes that "this station is Yokohama".
[0141] In the case w...
no. 3 approach
[0164] The third embodiment describes a sequence of generating a new standard pattern to control settings of a mobile terminal equipped with a voice recognition device (for example, settings when e-mail is received) by a user's voice.
[0165] A user can change a screen displayed on a display unit of his mobile terminal or a ringing sound when an e-mail is received, and select a folder in which e-mails are accumulated.
[0166] In general, the screen or ringtone when mail is received is changed by operating the enter key. However, since the operation keys of the mobile terminal are small, it is inconvenient for the user to operate such keys. Therefore, it is convenient to change the screen or ringtone by inputting voice instead of keys.
[0167] The term "display settings" includes display settings of the standby screen of the phone and display settings of downloaded games in addition to the display settings of e-mails. Generally, when changing the setting of the mobile term...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
