Abstract: Acoustic features are batched into two different batches. The second batch of the two batches is made in response to a detection of a word hypothesis output by a speech recognition network that received the first batch. The number of acoustic feature frames of the second batch is equal to a second batch size greater than the first batch size. The second batch is also to the speech recognition network for processing.

Abstract: A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Abstract: A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Abstract: A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Abstract: A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Abstract: A method for generating color Doppler images is implemented in real time using digital processing steps implemented on multi-purpose microprocessors. Processing is reduced by estimating velocity only when a tissue threshold decision for a given sample indicates that the sample is not tissue. Arc tangent calculations in the velocity estimation are performed using simplified look-up tables without sacrificing accuracy. One look-up table is lineraly quantized. A second is nonlinearly quantized.

Abstract: A scan conversion method is implemented to achieve real-time scan conversion at video rates. Scan conversion tasks include vector point identification processing, distance derivation processing and interpolation processing. An active image area is defined in response to user inputs. For a given set of user adjustments there is a fixed active image area of the display screen. In addition, there is a fixed positional relationship between output pixel locations of the active image and corresponding input vector points of the active image. Whenever the user makes adjustments, these relationships change becoming fixed again until another user-initiated change. Whenever the relationships change, vector identification processing and distance derivation processing is re-done to define these relationships. Interpolation processing is performed each frame only for output pixels within the active image area. The active image area is divided into groups of output pixels.

Abstract: An ultrasound signal processing apparatus provides a programmable platform for various clinical ultrasound applications. The apparatus is part of an ultrasound medical diagnostic imaging system. Data is processed in real-time, near real-time or in delayed playback. In one embodiment a pair of multi-processors are coupled to shared memory via a cross-bar switch. System control data is input via a VME interface. Ultrasound data is input via frame buffers. A first multi-processor manages vector data transfers and scan-converted data acquisitions. A second multi-processor manages video data output. The two multi-processors split signal processing tasks. In various configurations the apparatus executes vector processing, scan conversion, image processing and/or video processing tasks.