Abstract: In an image/video encoding and decoding system employing an artifact evaluator a method and/or apparatus to process video blocks comprising a decoder operable to synthesize an un-filtered reconstructed video block or frame and an artifact filter operable to receive the un-filtered reconstructed video block or frame, which generates a filtered reconstructed video block or frame. A memory buffer operable to store either the filtered reconstructed video block or frame or the un-filtered reconstructed video block or frame, and an artifact evaluator operable to update the memory buffer after evaluating and determining which of the filtered video block or frame, or the un-filtered video block or frame yields better image/video quality.

Abstract: In an image/video encoding and decoding system employing an artifact evaluator a method and/or apparatus to process video blocks comprising a decoder operable to synthesize an un-filtered reconstructed video block or frame and an artifact filter operable to receive the un-filtered reconstructed video block or frame, which generates a filtered reconstructed video block or frame. A memory buffer operable to store either the filtered reconstructed video block or frame or the un-filtered reconstructed video block or frame, and an artifact evaluator operable to update the memory buffer after evaluating and determining which of the filtered video block or frame, or the un-filtered video block or frame yields better image/video quality.

Abstract: Video encoding techniques are described. In one example, a video encoding technique includes identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame to be encoded, wherein the video blocks in the set are spatially located at defined locations relative to a current video block of the video frame to be encoded. A motion estimation routine can then be initialized for the current video block at the identified pixel location. By identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame, the phenomenon of spatial redundancy can be more readily exploited to accelerate and improve the encoding process.

Abstract: A dynamically scaled file encoding method and apparatus are disclosed. A file encoding system using JPEG encoding can be configured to produce relatively constant compressed file sizes irrespective of the initial file size and file contents. The system retrieves an initial file or image that is to be compressed and determines a target bit rate corresponding to the compressed file. The target bit rate is used to determine an initial scaling factor. The initial file is encoded using a JPEG encoder having coefficients scaled by the initial scaling factor. The resultant bit rate can be adjusted in a second loop if greater than the desired bit rate. To adjust the bit rate, a recomputed scaling factor is determined from the resultant bit rate. The initial file is then encoded with coefficients scaled by the recomputed scaling factor to achieve a bit rate that is within the target bit rate.

Abstract: Image processing techniques are described that reduce the amount of bandwidth required to read an image from memory for display. According to the techniques, a processor stores low change rate display layers in a memory such that a processor can read the display layers from the memory using a reduced amount of processing resources. An overlay module blends low change rate display layers into a combined overlay layer. A processor reads the overlay layer from the memory and selectively processes the overlay layer based on processing information for the overlay layer recorded in memory. The processor then blends the overlay layer and a high change rate video display layer to update a single image for display according to a high change rate. In addition, the overlay module updates the overlay layer based on the low change rate display layers according to a low change rate.

Abstract: In an image/video encoding and decoding system employing an artifact evaluator a method and/or apparatus to process video blocks comprising a decoder operable to synthesize an un-filtered reconstructed video block or frame and an artifact filter operable to receive the un-filtered reconstructed video block or frame, which generates a filtered reconstructed video block or frame. A memory buffer operable to store either the filtered reconstructed video block or frame or the un-filtered reconstructed video block or frame, and an artifact evaluator operable to update the memory buffer after evaluating and determining which of the filtered video block or frame, or the un-filtered video block or frame yields better image/video quality.

Abstract: A dynamically scaled file encoding method and apparatus are disclosed. A file encoding system using JPEG encoding can be configured to produce relatively constant compressed file sizes irrespective of the initial file size and file contents. The system retrieves an initial file or image that is to be compressed and determines a target bit rate corresponding to the compressed file. The target bit rate is used to determine an initial scaling factor. The initial file is encoded using a JPEG encoder having coefficients scaled by the initial scaling factor. The resultant bit rate can be adjusted in a second loop if greater than the desired bit rate. To adjust the bit rate, a recomputed scaling factor is determined from the resultant bit rate. The initial file is then encoded with coefficients scaled by the recomputed scaling factor to achieve a bit rate that is within the target bit rate.

Abstract: Generally stated a method and an accompanying apparatus provides for a voice recognition system (300) with programmable front end processing unit (400). The front end processing unit (400) requests and receives different configuration files at different times for processing voice data in the voice recognition system (300). The configuration files are communicated to the front end unit via a communication link (310) for configuring the front end processing unit (400). A microprocessor may provide the front end configuration files on the communication link at different times.

Abstract: A method and system for speech recognition combines different types of engines in order to recognize user-defined digits and control words, predefined digits and control words, and nametags. Speaker-independent engines are combined with speaker-dependent engines. A Hidden Markov Model (HMM) engine is combined with Dynamic Time Warping (DTW) engines.

Abstract: Video encoding techniques are described. In one example, a video encoding technique includes identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame to be encoded, wherein the video blocks in the set are spatially located at defined locations relative to a current video block of the video frame to be encoded. A motion estimation routine can then be initialized for the current video block at the identified pixel location. By identifying a pixel location associated with a video block in a search space based on motion vectors associated with a set of video blocks within a video frame, the phenomenon of spatial redundancy can be more readily exploited to accelerate and improve the encoding process.

Abstract: Generally stated a method and an accompanying apparatus provides for a voice recognition system (300) with programmable front end processing unit (400). The front end processing unit (400) requests and receives different configuration files at different times for processing voice data in the voice recognition system (300). The configuration files are communicated to the front end unit via a communication link (310) for configuring the front end processing unit (400). A microprocessor may provide the front end configuration files on the communication link at different times.

Abstract: A voice recognition (VR) system is disclosed that utilizes a combination of speaker independent (SI) and speaker dependent (SD) acoustic models. At least one SI acoustic model is used in combination with at least one SD acoustic model to provide a level of speech recognition performance that at least equals that of a purely SI acoustic model. The disclosed hybrid SI/SD VR system continually uses unsupervised training to update the acoustic templates in the one or more SD acoustic models.

Abstract: A method and system for voice recognition combines different types of voice recognition (VR) engines in order to recognize user-defined digits and control words, predefined digits and control words, and nametags. Speaker-independent VR engines are combined with speaker-dependent VR engines. A Hidden Markov Model (HMM) VR engine is combined with Dynamic Time Warping (DTW) engines.