Back to results
US 9,311,394 B2Granted
Speech recognition for internet video search and navigation
AssigneeSony Corporation
InventorBehram Mario Dacosta
Life of this patent
Estimating the term…
Abstract
Speech representing a desired video site or video subject is detected and digitized at a TV remote, and then sent to a TV. The TV or in some embodiments an Internet server communicating with the TV use speech recognition principles to recognize the speech, enter a database using the recognized speech as entering argument, and return a link to an Internet site hosting the desired video. The link can be displayed on the TV for selection thereof by a user to retrieve the video.
Claims12
A system, comprising:
- a TV communicating with the Internet;
- at least one remote control device wirelessly communicating with the TV;
- at least one microphone on the remote control device, the remote control device digitizing speech signals of a viewer of the TV and representing a viewer desired video site or video subject from the microphone and sending the signals to the TV;
- at least one processor coupled to the TV and implementing speech recognition on received speech signals representing a desired video site or video subject to generate recognized speech;
- and
- the processor accessing at least one database containing at least one index correlating speech with Internet addresses using the recognized speech to return at least one Internet address of an Internet site, wherein the database includes at least one index derived by the processor from closed captioned text in a televised video program received by the TV and provided to the processor.
3 more elements
A method for returning an Internet address of an Internet site storing a desired video, comprising:
- accessing closed captioned text received in televised video program;
- digitizing speech input to a TV remote by a viewer of the TV, the speech being related to the video;
- sending the speech to a TV;
- recognizing at least phonemes in the speech;
- and
- using the phonemes as entering argument, accessing a database including an index derived from the closed captioned text received in the televised video program to retrieve the Internet address.
3 more elements
A computer program product comprising:
- a non-transitory computer-readable medium executable by a processor to cause the processor to undertake method acts comprising:
- recognizing a viewer's digitized speech representing a video and generating recognized speech in response;
- accessing a data structure correlating speech representing video to Internet addresses of sites storing the video, the data structure being generated at least in part using metadata received in video presented on the TV and/or closed caption text received in video presented on the TV;
- and
- retrieving, from the data structure, at least one Internet address correlated to a match of the recognized speech, wherein the processor and medium are wholly contained within the TV and/or the remote control without resorting to accessing a server to undertake the method acts, a limited grammar database being maintained in the TV so that memory and processing requirements to process the limited grammar database are manageable within the confines of the processor and medium, the limited grammar database including indices derived at least from the closed captioned text received by the TV for a past “X” bytes and/or a past “Y” hours, the limited grammar database not including indices derived from the closed captioned text received by the TV in excess of the past “X” bytes and/or received earlier than the past “Y” hours, such that a match to the recognized speech is returned only if the recognized speech contains content that has occurred during the broadcast in the past “Y” hours and/or if it has occurred in the past “X” bytes.
2 more elements
Dependencies are inferred from the claim text.