Unlock instant, AI-driven research and patent intelligence for your innovation.

System and method of access and retrieval for media file using speech recognition

A media file and speech recognition technology, applied in speech recognition, speech analysis, digital data information retrieval, etc.

Inactive Publication Date: 2009-06-03
PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Unfortunately, the application of speech recognition to embedded devices does not make speech recognition no longer just an input in human-computer interaction. The examples of human-computer interaction mainly include buttons, micro-adjustment dials, and touch screens.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method of access and retrieval for media file using speech recognition
  • System and method of access and retrieval for media file using speech recognition
  • System and method of access and retrieval for media file using speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The following detailed description of the preferred embodiments is merely exemplary in nature, and is not intended to limit the present invention and its application or use.

[0013] According to the invention and reference figure 1 , the embedded device 100 has a limited display 102 and multi-function operation buttons 104 for displaying playlists. Along with audio input 108 and audio output 110, a micro-dial 106 is also provided. A data storage 112 such as a Secure Digital (SD) card or the like is also provided. The embedded device 100 may access a computer network 114, such as the Internet, through a data link 116, such as wireless or Bluetooth.

[0014] In operation, the user navigates the computer network 114 using voice input and / or manual input and locates media files 118 of interest. For example, a user may download media files 118 to data storage 112 for future access at their leisure. In another example, a user may use an electronic activity guide (EAG) 12...

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

No PUM Login to View More

Abstract

An embedded device for playing media files, which can generate a media file playlist based on the user's input voice. The embedded device includes an indexer that generates a plurality of speech recognition grammars. According to an aspect of the invention, the indexer generates a speech recognition grammar based on the content of a media file header of the media file. According to another aspect of the invention, the indexer generates a speech recognition grammar based on categories in a file path for retrieving media files from a user location. When the speech recognizer receives input speech from the user in selection mode (404), the media file selector compares the input speech received in selection mode with a plurality of speech recognition grammars (410), thereby selecting a media file (418 ).

Description

technical field [0001] The present invention generally relates to methods and systems for indexing and retrieval, and more particularly, to using speech recognition to select media files based on textual descriptions of files. Background technique [0002] Embedded devices such as MP3 players for playing media files have limited display and manual input capabilities. For example, due to the limited space, the display space is not very large, so a large amount of information cannot be displayed. Also, due to limited space, not many function keys can be provided, so full text entry is difficult and often impossible. As a result, tasks such as finding, storing, and retrieving MP3 files are labor-intensive and often laborious for users to perform. For these reasons and some similar reasons, embedded devices have been developed that use speech recognition to access various databases. [0003] Unfortunately, the application of speech recognition to embedded devices has not made...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L21/00G10L15/00G06F17/30G10LG10L11/00G10L15/04G10L15/06G10L15/18G10L15/26
CPCY10S707/99935Y10S707/99933G10L15/183G10L15/19G10L15/265Y10S707/99934G06F17/30026G10L15/26G06F16/433
Inventor 大卫·克瑞兹卢卡·里加兹帕特里克·恩伽元让-克劳德·容科
Owner PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA