Abstract: Chinese name transliteration is described. A Chinese name including a surname followed by a given name is received. The received Chinese name is parsed into a surname and a given name by: identifying any dual-character surnames in the received Chinese name, by referencing a list of known Chinese surnames; identifying any single-character surnames in the received Chinese name, by referencing the list of known Chinese surnames; and identifying, among the remaining characters in the received Chinese name, any characters not belonging to a dual-character or a single-character surname as a given name. The identified surname and the identified given name are transliterated into a Mandarin Pinyin representation. The Mandarin Pinyin representation of the surname and the given name is normalized into a pre-determined representation.

Abstract: Chinese name transliteration is described. A Chinese name including a surname followed by a given name is received. The received Chinese name is parsed into a surname and a given name by: identifying any dual-character surnames in the received Chinese name, by referencing a list of known Chinese surnames; identifying any single-character surnames in the received Chinese name, by referencing the list of known Chinese surnames; and identifying, among the remaining characters in the received Chinese name, any characters not belonging to a dual-character or a single-character surname as a given name. The identified surname and the identified given name are transliterated into a Mandarin Pinyin representation. The Mandarin Pinyin representation of the surname and the given name is normalized into a pre-determined representation.

Abstract: Concealing a lost audio frame of a received audio signal by performing a sinusoidal analysis of a part of a previously received or reconstructed audio signal, wherein the sinusoidal analysis involves identifying frequencies of sinusoidal components of the audio signal, applying a sinusoidal model on a segment of the previously received or reconstructed audio signal, wherein said segment is used as a prototype frame in order to create a substitution frame for a lost audio frame, and creating the substitution frame for the lost audio frame by time-evolving sinusoidal components of the prototype frame, up to the time instance of the lost audio frame, in response to the corresponding identified frequencies.

Abstract: An apparatus, such as a display device, may have a processor, memory storing computer-readable instructions, and a display portion. The apparatus may obtain one or more second files in response to converting a first file into the one or more second files. The plurality of second files may be obtained one by one. The apparatus may determine whether all of one or more selected files from among the one or more second files have been obtained, prior to obtaining all of the one or more second files. The one or more selected files may be a subset of the one or more second files. The apparatus may also output the one or more selected files in response to determining that all of the one or more selected files have been obtained.

Abstract: Described herein are various technologies pertaining to a multilingual deep neural network (MDNN). The MDNN includes a plurality of hidden layers, wherein values for weight parameters of the plurality of hidden layers are learned during a training phase based upon training data in terms of acoustic raw features for multiple languages. The MDNN further includes softmax layers that are trained for each target language separately, making use of the hidden layer values trained jointly with multiple source languages. The MDNN is adaptable, such that a new softmax layer may be added on top of the existing hidden layers, where the new softmax layer corresponds to a new target language.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for language models using non-linguistic context. In some implementations, context data indicating non-linguistic context for the utterance is received. Based on the context data, feature scores for one or more non-linguistic features are generated. The feature scores for the non-linguistic features are provided to a language model trained to process scores for non-linguistic features. The output from the language model is received, and a transcription for the utterance is determined using the output of the language model.

Abstract: A social networking system user may request physical prints of digital photographs stored in connection with the user's user profile on the social networking system. The physical prints are generated by a photograph developer, such as a retail store, and retrieved by the user. The user may request the physical prints from an application executing on a user device that allows the user to identify social context information associated with a digital photograph for inclusion on the physical print. The social networking system may notify users connected to the user and/or to the digital image of the physical print generation.

Abstract: The present technology relates to an encoding device and an encoding method, a decoding device and a decoding method, and a program, configured to obtain a high quality audio with less encoding amount. A number-of-sections determining feature amount calculating circuit calculates a number-of-sections determining feature amount for determining the number of divisions to divide a process target section into continuous frame sections each including a frame for which the same estimation coefficient is selected, based on sub-band signals of a plurality of sub-bands constituting an input signal.

Abstract: A voice input device provided with an input section for inputting a voice of a user, a recognition section for recognizing the voice of the user inputted by the input section, a generation section for generating characters or a command based on a recognition result of the recognition section, a detection section for detecting a device's own posture, and an instruction section for instructing the generation section to generate the command when a detection result of the detection section represents a specific posture as compared to instructing the generation section to generate the characters when the detection result of the detection section represents a posture other than the specific posture. Accordingly, character input and command input during dictation is correctly distinguished, or more specifically unexpected character input during dictation is avoided.

Abstract: A method is provided in one embodiment and includes establishing a communication session involving a first endpoint and a second endpoint that are associated with a session, the first endpoint being associated with a first identifier and the second endpoint being associated with a second identifier. The method also includes evaluating first data for the first endpoint; evaluating second data for the second point; and determining whether to initiate a calendaring activity based, at least in part, on the first data and the second data. In more specific embodiments, the method includes evaluating a first availability associated with the first endpoint; evaluating a second availability associated with the second endpoint; and suggesting a future meeting based, at least in part, on the first availability and the second availability.

Abstract: A method for processing a voice command using a statistical dialog model determines a belief state as a probability distribution over states organized in a hierarchy with a parent-child relationship of nodes representing the states. The belief state includes the hierarchy of state variables defining probabilities of each state to correspond to the voice command and a probability of a state of a child node in the hierarchy is conditioned on a probability of a state of a corresponding parent node. A system action is selected based on the belief state.

Abstract: Techniques are described for discovering capabilities of voice-enabled resources. A voice-controlled digital personal assistant can respond to user requests to list available voice-enabled resources that are capable of performing a specific task using voice input. The voice-controlled digital personal assistant can also respond to user requests to list the tasks that a particular voice-enabled resource can perform using voice input. The voice-controlled digital personal assistant can also support a practice mode in which users practice voice commands for performing tasks supported by voice-enabled resources.

Abstract: Methods of printing a color image having more than one color comprise receiving multiple-bit image data comprising multiple-bit pixel values, deriving 1-bit image data comprising first and second sets of 1-bit image data, and printing from the 1-bit image data the color image. Methods of generating 1-bit image data for a color image having more than one color comprise receiving multiple-bit image data comprising multiple-bit pixel values, and electronically deriving a first set and a second set of 1-bit image data.

Abstract: A print controlling apparatus includes a user interface to input a printing command of a document displaying a plurality of overlaid objects, a printing data generator to detect a transparency region where a transparency is set, in the overlaid objects, to generate a transparency image by calculating a pixel value of the transparency region, based on the pixel value of each object and the transparency, and to generate printing data comprising the transparency image, and a communication interface to send the printing data to the image forming apparatus.

Abstract: In low-resolution processing (reduction processing) in which input image data is separated into character print data and image print data to generate print data of lower resolution than that of the input image data, if a plurality of pixels is simply reduction-processed to one pixel, color of a color image surrounding a character may change. In an image processing method, calculation for performing reduction processing so that the plurality of pixels in the input image data corresponds to one pixel in the print data is performed as follows. A ratio of using a pixel value of a character attribute pixel in the calculation is set to 0, or set smaller than a ratio of using a pixel value of an image attribute pixel. As a result, a change in the color of the color image surrounding the character can be prevented.

Abstract: Disclosed are an ideographical member identification and extraction method and a machine-translation and manual-correction interactive translation method thereof. The ideographical member identification and extraction method is using corpuses with the same contents in a multi-language or bilingual word version, aligning sentences to generate a double-statement opposite library, different languages and characters being related through ideographical expressions, and the ideographical expressions of different languages and characters being achieved through four identical ideographical members. Identifying and extracting the four identical ideographical members comprises a sentence reading matched frame, an identification and label sentence cabin, a cabin detection and extraction cabin model and a receiving and storing sense-group cluster.

Abstract: A device selecting apparatus is provided, which includes a display unit, a communication unit configured to connect the device selecting apparatus communicably with one or more devices therethrough, a controller configured to display, on the display unit, a list of one or more identifiers of the one or more devices, to receive, from a specified device, device information for identifying the specified device via the communication unit, and to perform a selection process to put, into a selected state, an identifier of the specified device identified by the device information received via the communication unit, on the list displayed on the display unit.

Abstract: In a method for document analysis, receiving a request to translate a document, identifying usage information corresponding to the document, wherein the usage information includes information corresponding to a current viewing session of the document and historical usage information corresponding to one or more previous viewing sessions of the document, and determining one or more sections of the document to translate based on the identified usage information corresponding to the document.

Abstract: A method for maintaining conversational cadence may include determining, by a processor, a conversational cadence associated with a user in a social network. The conversational cadence may be determined based on a plurality of messages previously transmitted by the user. The method may also include detecting, by the processor, a reduction in the conversational cadence of the user. The method may further include providing, by the processor, a set of fill-in messages that create an appearance to another user in the social network that there is no reduction in the conversational cadence.

Abstract: A method for maintaining conversational cadence may include determining, by a processor, a conversational cadence associated with a user in a social network. The conversational cadence may be determined based on a plurality of messages previously transmitted by the user. The method may also include detecting, by the processor, a reduction in the conversational cadence of the user. The method may further include providing, by the processor, a set of fill-in messages that create an appearance to another user in the social network that there is no reduction in the conversational cadence.