Abstract: A system includes acquisition of a domain grammar, determination of an interpolated grammar based on the domain grammar and a base grammar, determination of a delta domain grammar based on an augmented first grammar and the interpolated grammar, determination of an out-of-vocabulary class based on the domain grammar and the base grammar, insertion of the out-of-vocabulary class into a composed transducer composed of the augmented first grammar and one or more other transducers to generate an updated composed transducer, composition of the delta domain grammar and the updated composed transducer, and application of the composition of the delta domain grammar and the updated composed transducer to an output of an acoustic model.

Abstract: Generally discussed herein are devices, systems, and methods for wake word verification. A method can include receiving, at a server, a message from a device indicating that an utterance of a user-defined wake word was detected at the device, the message including (a) audio samples or features extracted from the audio samples and (b) data indicating the user-defined wake word, retrieving or generating, at the server, a custom decoding graph for the user-defined wake word, wherein the decoding graph and the static portion of the wake word verification model form a custom wake word verification model for the user-defined wake word, executing the wake word verification model to determine a likelihood that the wake word was uttered, and providing a message to the device indicating whether wake was uttered based on the determined likelihood.

Abstract: A system includes acquisition of a domain grammar, determination of an interpolated grammar based on the domain grammar and a base grammar, determination of a delta domain grammar based on an augmented first grammar and the interpolated grammar, determination of an out-of-vocabulary class based on the domain grammar and the base grammar, insertion of the out-of-vocabulary class into a composed transducer composed of the augmented first grammar and one or more other transducers to generate an updated composed transducer, composition of the delta domain grammar and the updated composed transducer, and application of the composition of the delta domain grammar and the updated composed transducer to an output of an acoustic model.

Abstract: Generally discussed herein are devices, systems, and methods for wake word verification. A method can include receiving, at a server, a message from a device indicating that an utterance of a user-defined wake word was detected at the device, the message including (a) audio samples or features extracted from the audio samples and (b) data indicating the user-defined wake word, retrieving or generating, at the server, a custom decoding graph for the user-defined wake word, wherein the decoding graph and the static portion of the wake word verification model form a custom wake word verification model for the user-defined wake word, executing the wake word verification model to determine a likelihood that the wake word was uttered, and providing a message to the device indicating whether wake was uttered based on the determined likelihood.

Abstract: A trial based layout builder generates multiple trial multi-column layouts for content until a multi-column layout that satisfies particular criteria for multi-column balancing is generated. Multiple trial multi-column layouts can be generated in parallel based on different boundaries until a layout that does satisfy the criteria is identified. Different elements of the content laid out in different trial multi-column layouts can be reused in subsequently generated trial multi-column layouts. The content can also optionally be separated into multiple different portions at various break points, and trial multi-column layouts for the different portions can be generated in parallel. Additionally, if a trial multi-column layout for one of the portions that satisfies the particular criteria is identified, the content in that portion can be displayed while continuing to attempt to identify a layout for the content of the other portion that satisfies the one or more criteria.

Abstract: A handwriting recognition system is described that includes a language model with scoring to improve recognition accuracy, such as for words outside of a selected language model. The handwriting recognition system increases the accuracy of handwriting recognizers that perform segmentation of ink into atomic elements (segments) and then classify each ink segment separately. After segmentation, a shape classifier estimates the class (letter) probabilities for each segment of ink by producing a corresponding score. The system applies the language model scoring to the shape classification results and typically selects the class with the highest score as the recognition result. Because the language model is not too restrictive, it works well for recognizing any word, even those that would not be in a dictionary for the current language. Thus, the handwriting recognition system produces better recognition results and can often recognize words that dictionary-based language models would not recognize correctly.

Abstract: A trial based layout builder generates multiple trial multi-column layouts for content until a multi-column layout that satisfies particular criteria for multi-column balancing is generated. Multiple trial multi-column layouts can be generated in parallel based on different boundaries until a layout that does satisfy the criteria is identified. Different elements of the content laid out in different trial multi-column layouts can be reused in subsequently generated trial multi-column layouts. The content can also optionally be separated into multiple different portions at various break points, and trial multi-column layouts for the different portions can be generated in parallel. Additionally, if a trial multi-column layout for one of the portions that satisfies the particular criteria is identified, the content in that portion can be displayed while continuing to attempt to identify a layout for the content of the other portion that satisfies the one or more criteria.

Abstract: Techniques involving dynamic colorization of graphical user interfaces. One representative technique includes enabling a user to specify colors in which user interface elements will be colored in an application. An application colorization service is initiated in response to the user specification of the colors, which is used at least to obtain the colors specified by the user, and to create bitmap images of the application's user interface elements using the user-specified colors. A bitmap image output location is made accessible to the application to enable the application to retrieve the created bitmap images, and present the application using the application user interface elements having the user-specified colors.

Abstract: A handwriting recognition system is described that includes a language model with scoring to improve recognition accuracy, such as for words outside of a selected language model. The handwriting recognition system increases the accuracy of handwriting recognizers that perform segmentation of ink into atomic elements (segments) and then classify each ink segment separately. After segmentation, a shape classifier estimates the class (letter) probabilities for each segment of ink by producing a corresponding score. The system applies the language model scoring to the shape classification results and typically selects the class with the highest score as the recognition result. Because the language model is not too restrictive, it works well for recognizing any word, even those that would not be in a dictionary for the current language. Thus, the handwriting recognition system produces better recognition results and can often recognize words that dictionary-based language models would not recognize correctly.