Matsushita Electric Industrial Co., Ltd.

Ikuo Inoue

Akiyoshi Tanaka

Atsushi Nagata

Mitsuru Endo

Wataru Fujikawa

Masakatsu Hoshimi

Hitoshi Yashio

Satoshi Matsuya

Hiroshi Furuyama

Hiroyuki Uwabo

Satoru Fujii

Katsuyuki Niyada

Shuji Morii

Satoshi Matsuya, Deceased

A video retrieval data generation apparatus includes an extractor that is configured to extract a characteristic pattern from a voice signal synchronous with a video signal. The video retrieval data generation apparatus also includes an index generator that is configured to set the voice signal for a voice period as a processing target. The index generator is further configured to prepare standard voice patterns of a subword corresponding to a plurality of subwords, detect, for each subword, a characteristic pattern similar to a standard voice pattern at each of the voice periods, and generate, for each subword, an index containing time synchronization information corresponding to a position where the similar characteristic pattern is detected. The video retrieval data generation apparatus also includes a multiplexer that is configured to multiplex video signals, voice signals and indexes to output in a data stream format.

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

A video retrieval apparatus includes a retrieval data generator that is configured to extract a characteristic pattern from a voice signal synchronous with a video signal to generate an index for video retrieval. The video retrieval apparatus also includes a retrieval processor that is configured to input a key word from a retriever and collate the key word with the index to retrieve a desired video. The retrieval data generator includes a multiplexor that is configured to multiplex video signals, voice signals and indexes to output in data stream format. The 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 may collate a visual pattern of the key word visual pattern data of the video signal at the time a person vocalizes a sound as the index for retrieval.

A motion compensated prediction interframe coding system which first measures characteristics regarding the fineness of a pattern or texture of a picture, which is represented by an input television signal and is divided into a group of continuous blocks each quantized by using a quantization step size, and changes the quantization step size into a smaller one if quantizes a block having a picture pattern or texture finer than patterns of the other blocks. Thereby, an amount of generated codes can be limited but a motion compensated prediction frame coding operation can be performed without degrading the fineness of the texture of the original input picture.

Motion compensated prediction interframe coding system

A video signal encoding apparatus of the type in which inter-frame difference values for respective picture elements are subjected to orthogonal transform processing and the resultant transform coefficients are quantized and encoded, with respective values of quantization step size applied to successive 2-dimensional blocks of picture element values being varied such as to control the encoded data bit stream to a constant bit rate, in which the quantization step size for each block is also controlled in accordance with whether or not the block lies on a border between a visually smooth region of the picture expressed by the video signal and a region in which substantial changes occur in the picture. The step size can thereby be set to be sufficiently small, in the case of specific blocks for which is necessary to use a small size of quantization step in order to prevent noise from appearing in the picture obtained from the decoded video signal.

Video signal encoding apparatus utilizing control of quantization step

A motion compensated prediction interframe coding system which includes a first checking portion for judging whether a motion compensation of a coding block is effective and outputting a motion compensation control signal representing the result of the judgement, a storage portion for storing motion vectors of the coding block and adjacent blocks and the motion compensation control signal, a second checking portion for comparing the motion vector of the coding block, of which the motion compensation should be effected, with each of the motion vectors of the adjacent blocks, of which the motion compensation should be effected, and judging that the intra-loop filtering processing to be performed after the motion compensation is ineffective if the number of the adjacent blocks, of which the motion vectors are identical with that of the coding block, is equal to or more than a predetermined number and that the filtering processing performed after the motion compensation is effective in another case, a motion-compensated brightness calculating portion for calculating motion-compensated brightness of pixels of the blocks, of which the motion compensation is effected, and a predictive brightness calculating portion for calculating predictive brightness of the pixels of the blocks by performing the filtering processing of the motion-compensated brightness of the pixels only if the filtering processing is effective. Thereby, the amount of the generated prediction error signals are reduced, and the picture quality is improved.

Apparatus for speech recognition, having each phoneme as a fundamental recognition unit, recognizes input speech by discriminating phonemes in the input speech. The apparatus comprises a memory for storing phoneme standard patterns of phonemes or phoneme groups; a spectrum analyzer for obtaining parameters indicative of the input speech signal spectrum; a statistical distance measure similarity calculator calculates the degree of similarity between the output of the spectrum analyzer and standard patterns stored in the memory; a segmentation portion for segmenting by using time-dependent low- and high-frequency power variations of the input speech signal and results from the similarity calculator; and a phoneme discriminator for recognizing phonemes by using the results from the similarity calculator.

Growing community of inventors

Yokohama, Japan

Ikuo Inoue