Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1998-12-23
2001-06-05
{haeck over (S)}mits, T{overscore (a)}livaldis I. (Department: 2641)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S251000, C704S270000, C704S271000, C704S260000
Reexamination Certificate
active
06243676
ABSTRACT:
BACKGROUND
The invention relates to searching and retrieving multi-media information.
Rapid advances in computer technology have resulted in an explosion of electronically accessible information. For instance, virtually any information imaginable is available on information sources such as specialized databases and servers. The information can be accessed from the convenience of the user's computer, or may be accessed using a telephone which can relay information and allow their users to respond quickly to various situations. The advent of wireless telephones has further allowed users access to information regardless of the user's proximity to a telephone jack.
The availability of these information sources renders information, formerly hard to manage and retrieve, readily accessible. To date, the advantages associated with the widespread availability of electronic data have not been fully realized due to a variety of reasons. For instance, not all information is stored or available in the same format so that the information can be easily searched. This situation occurs when information is stored variously as video clips, sound files and text files. More particularly, information such as sound cannot be searched using conventional text search commands. Moreover, certain perishable and high value-added information such as news on business, sports, current events and entertainment are best presented in audio-visual form and multimedia form rather than text form. Yet, such sources of audio-visual/multimedia information can be prolific and can strain the processing and data storage capacity of a computer hosting such information. Examples of prolific sources of audio-visual/multimedia information include television feeds, cable feeds, radio feeds, and computer generated multimedia feeds.
SUMMARY OF THE INVENTION
In one aspect, a method is disclosed for retrieving a multi-media segment from a signal stream having an audio component and a closed caption component. The method includes separating the audio component and the closed caption component from the signal stream; generating an audio pattern representative of the start of the multi-media segment; locating the audio pattern in the audio component; and temporally aligning the text with the audio pattern in the audio component.
Implementations of the invention include one or more of the following. The method includes retrieving text from the closed caption component; and comparing the text against one or more keywords delimiting the multi-media segment. The keywords may delimit the start and the end of the multi-media segment, or may be stored in a dictionary. The method may compare the text against one or more key characters delimiting the multi-media segment. The key characters may be stored in a dictionary. The method may include generating a concluding audio pattern representative of the end of the multi-media segment; and locating the concluding audio pattern in the audio component. The method may identify the multi-media segment between the audio patterns. The multi-media segment and text may be indexed in a database. The multi-media segment may be played on-demand.
In another aspect, an apparatus retrieves a multi-media segment from a signal stream, the signal stream having an audio component and a closed caption component. The apparatus includes means for separating the audio component and the closed caption component from the signal stream; means for generating an audio pattern representative of the start of the multi-media segment;means for locating the audio pattern in the audio component; and means for temporally aligning the text with the audio pattern in the audio component.
Implementations of the invention include one or more of the following. The apparatus may include means for retrieving text from the closed caption component; and means for comparing the text against one or more keywords delimiting the multi-media segment. The keywords may delimit the start and the end of the multi-media segment. The keywords may be stored in a dictionary. A means for comparing the text against one or more key characters delimiting the multi-media segment may be provided. The key characters may be stored in a dictionary. The apparatus may include means for generating a concluding audio pattern representative of the end of the multi-media segment; and means for locating the concluding audio pattern in the audio component. A means for identifying the multi-media segment between the audio patterns may be used. The multi-media segment and text may be indexed in a database. The apparatus may include a means for playing the multi-media segment on-demand.
In a third aspect, an apparatus retrieves a multi-media segment from a signal stream, the signal stream having an audio component and a text component. The apparatus includes a decoder for separating the audio component and the text component from the signal stream; an audio synthesizer coupled to the decoder for generating an audio pattern representative of the start of the multi-media segment; a pattern recognizer coupled to the decoder and to the audio synthesizer for locating the audio pattern in the audio component; and an aligner coupled to the pattern recognizer and to the decoder for temporally aligning the text with the audio pattern in the audio component.
Implementations of the invention include one or more of the following. The apparatus may include an extractor for retrieving text from the closed caption component; and a comparator for checking the text against one or more keywords delimiting the multi-media segment. The keywords may delimit the start and the end of the multi-media segment. A dictionary may store the keywords. The text may be compared against one or more key characters delimiting the multi-media segment. A character dictionary may store the key characters. The synthesizer may generate a concluding audio pattern representative of the end of the multi-media segment and the pattern recognizer locates the concluding audio pattern in the audio component. A database may store the multi-media segment between the audio patterns and the text.
In another aspect, a method for retrieving a multi-media segment from a signal stream, the signal stream having an audio component and a text component, includes generating audio patterns representative of the start and the end of the multi-media segment; locating the audio patterns in the audio component; and delimiting a portion of the audio component between the audio patterns as the multi-media segment.
Implementations of this aspect may include temporally aligning the text with the start of the delimited audio component portion; and storing the text and the delimited audio component portion in a database.
In another aspect, a computer system includes a plurality of interdependent processors, each interdependent processor executing an independent operating system image without sharing file system state information. Each interdependent processor has a network access card with a first network connection and a second network connection; and each interdependent processor has a decoder for separating the audio component and the text component from the signal stream; an audio synthesizer coupled to the decoder for generating an audio pattern representative of the start of the multi-media segment; a pattern recognizer coupled to the decoder and to the audio synthesizer for locating the audio pattern in the audio component; an aligner coupled to the pattern recognizer and to the decoder for temporally aligning the text with the audio pattern in the audio component; and a database coupled to the aligner for storing the audio component with the aligned text. Each processor is connected to a first active backplane and to a second active backplane, the second active backplane operating in lieu of the first active backplane in case of a fail-over; and one or more peripherals connected to each of the first and second active backplanes and responsive to data requests transmitted over the first and second active backplanes.
Adva
Fish & Richardson P.C.
Nolan Daniel A.
Openwave Systems Inc.
{haeck over (S)}mits T{overscore (a)}livaldis I.
LandOfFree
Searching and retrieving multimedia information does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Searching and retrieving multimedia information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Searching and retrieving multimedia information will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2455489