Abstract: The present invention relates to speech recognition systems, especially to arranging detection of end-of utterance in such systems. A speech recognizer of the system is configured to determine whether recognition result determined from received speech data is stabilized. The speech recognizer is configured to process values of best state scores and best token scores associated with frames of received speech data for end of utterance detection purposes. Further, the speech recognizer is configured to determine whether end of utterance is detected or not, based on the processing, if the recognition result is stabilized.

Abstract: An approach is provided for providing a co-creation platform. A co-creation application extracts tags from a plurality of information sources reflecting the expertise of a user. The co-creation application creates a model of the user's expertise by applying a probabilistic analysis on the extracted tags. The co-creation application collects assignment information including at least one or more specified areas of expertise, and matches the model of the user's expertise against the specified areas of expertise.

Abstract: A system and method are proposed for measuring confusability or similarity between given entry pairs, including text string pairs and acoustic model pairs, in systems such as speech recognition and synthesis systems. A string edit distance (Levenshiten distance) can be applied to measure distance between any pair of text strings. It also can be used to calculate a confusion measurement between acoustic model pairs of different words and a model-driven method can be used to calculate a HMM model confusion matrix. This model-based approach can be efficiently calculated with low memory and low computational resources. Thus it can improve the speech recognition performance and models trained from text corpus.

Abstract: The present invention relates to speech recognition systems, especially to arranging detection of end-of utterance in such systems. A speech recognizer of the system is configured to determine whether recognition result determined from received speech data is stabilized. The speech recognizer is configured to process values of best state scores and best token scores associated with frames of received speech data for end of utterance detection purposes. Further, the speech recognizer is configured to determine whether end of utterance is detected or not, based on the processing, if the recognition result is stabilized.

Abstract: The invention relates to a method for detecting audio activity. In the method samples of audio signal are formed or received. A feature vector is formed from the samples of the audio signal and the feature vector is projected by a discriminant vector to form a projection value for the feature vector. A statistical value of a number of projection values is calculated, a minimum value and a maximum value of said number of projection values are detected. The method further comprises determining the existence of monitored audio activity on the basis of said minimum value, said maximum value and the projection value. The invention also relates to a speech decoder, a system, an electronic device, a module and a computer program product.