Abstract: Examples relate to a surgical microscope system and to a corresponding system, method and computer program for a surgical microscope system. The system comprises one or more processors and one or more storage devices. The system is configured to obtain an audio signal from a microphone of the surgical microscope system. The system is configured to analyze the audio signal locally to detect one or more spoken commands within the audio signal. A user-specific voice profile is used to determine whether the one or more spoken commands are uttered by a user associated with the user-specific voice profile. The system is configured to control the surgical microscope system based on the detected one or more spoken commands if the one or more spoken commands are uttered by the user associated with the user-specific voice profile.

Abstract: An anomaly detection apparatus extracts a circumstantial feature value for anomaly detection corresponding to a circumstantial feature value for learning from other modal signal for anomaly detection different in modal from acoustic, calculates a signal pattern feature related to an acoustic signal of anomaly detection target based on the acoustic signal of anomaly detection target, the circumstantial feature value for anomaly detection and a signal pattern model learned based on an acoustic signal for learning and the circumstantial feature value for learning calculated from other modal signal for learning, and calculates an anomaly score for performing an anomaly detection of the acoustic signal of anomaly detection target based on the signal pattern feature.

Abstract: Described is a technology by which a probability is estimated for a token in a sequence of tokens based upon a number of zero or more times (actual counts) that the sequence was observed in training data. The token may be a word in a word sequence, and the estimated probability may be used in a statistical language model. A discount parameter is set independently of interpolation parameters. If the sequence was observed at least once in the training data, a discount probability and an interpolation probability are computed and summed to provide the estimated probability. If the sequence was not observed, the probability is estimated by computing a backoff probability. Also described are various ways to obtain the discount parameter and interpolation parameters.

Abstract: Described is a calibration model for use in a speech recognition system. The calibration model adjusts the confidence scores output by a speech recognition engine to thereby provide an improved calibrated confidence score for use by an application. The calibration model is one that has been trained for a specific usage scenario, e.g., for that application, based upon a calibration training set obtained from a previous similar/corresponding usage scenario or scenarios. Different calibration models may be used with different usage scenarios, e.g., during different conditions. The calibration model may comprise a maximum entropy classifier with distribution constraints, trained with continuous raw confidence scores and multi-valued word tokens, and/or other distributions and extracted features.

Abstract: A computer-loadable data structure is provided that represents a state-and-transition-based description of a speech grammar. The data structure includes first and second transition entries that both represent transitions from a first state. The second transition entry is contiguous with the first transition entry in the data structure and includes a last-transition value. The last-transition value indicating that the second transition is the last transition from the first state in the data structure.