Method and apparatus for retrieving a video and audio scene using an index generated by speech recognition

A video retrieval apparatus comprising:

• a retrieval data generator that is configured to extract a characteristic pattern from a voice signal synchronous with a video signal to generate indexes for video retrieval;
• and
• a retrieval processor that is configured to input a key word from a retriever and collate the key word with the indexes to retrieve a desired video, said retrieval processor including a receiver that is configured to receive the key word from a retrieval terminal connected through a communications network, and said retrieval processor further including a transmitter that is configured to transmit a retrieved video signal to the retrieval terminal through the communications network;
• wherein said retrieval data generator includes a multiplexor that is configured to multiplex video signals, voice signals and indexes to output in data stream format;
• and
• wherein said retrieval processor includes a demultiplexor that is configured to demultiplex the multiplexed data stream into the video signals, the voice signals and the indexes.

A voice retrieval apparatus comprising:

• a retrieval data generator that is configured to extract a characteristic pattern from a voice signal to generate indexes for voice retrieval;
• and
• a retrieval processor that is configured to input a key word from a retriever and collate the key word with the indexes to retrieve a desired voice;
• wherein said retrieval data generator includes a multiplexor that is configured to multiplex video signals, voice signals and indexes to output in data stream format;
• and
• wherein said retrieval processor includes a demultiplexor that is configured to demultiplex the multiplexed data stream into the video signals, the voice signals and the indexes.

A video reproduction apparatus that performs reproduction of video signals, said apparatus comprising:

• a storage medium that stores video signals and that stores video retrieval indexes generated based on an input voice;
• a key word pattern converter that is configured to convert a key word input from a retriever into pattern collation data;
• and
• a key word pattern collator that is configured to collate the pattern collation data of the key word with pattern collation data in the video retrieval indexes of a video program stored in said storage medium;
• wherein said key word pattern converter converts the input key word into visual characteristic pattern data;
• and
• wherein said key word pattern collator collates the visual characteristic pattern data of the input key word with visual characteristic pattern data of the video signals at the time a person vocalizes a sound as the video retrieval indexes stored in said storage medium.