Abstract: An adaptive localization system translates and displays translated content to a user, for example through a website or application using the adaptive localization system. A user can view, receive, or otherwise interact with the translated content, which can be differently translated based on desired language, geographic location, an intended user, or other relevant characteristics of the viewing user. The adaptive localization engine can translate the inherent meaning of content rather than, for example, creating an exact grammatical or “word-for-word” translation of individual words or phrases in the content. The adaptive localization engine displays alternate variations of the same translation of content to different users and based on user response to the alternate translations, determines the accuracy or correctness of a certain translations of content and modifies future translations accordingly.

Abstract: There is provided an information processing server including a specification unit configured to specify an individual registered in a predetermined database on the basis of identification information sent from a near-field communication device and collected voice information.

Abstract: Systems and methods are described for processing and interpreting audible commands spoken in one or more languages. Speech recognition systems disclosed herein may be used as a stand-alone speech recognition system or comprise a portion of another content consumption system. A requesting user may provide audio input (e.g., command data) to the speech recognition system via a computing device to request an entertainment system to perform one or more operational commands. The speech recognition system may analyze the audio input across a variety of linguistic models, and may parse the audio input to identify a plurality of phrases and corresponding action classifiers. In some embodiments, the speech recognition system may utilize the action classifiers and other information to determine the one or more identified phrases that appropriately match the desired intent and operational command associated with the user's spoken command.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated quantitative assessment of text complexity. A system may include processing at least one body of text in a text-based query using a natural language processing engine. The processed text may include sub-blocks of text in a predetermined sequence size such as an n-gram. The system may compare reference bases to the processed text, where each reference base is associated with a different natural language. The system determines which of the reference bases has a highest number of matching words within the body of text, and thereby identifies the reference base as the source language of the supplied text. The system then determines an average complexity score for n-gram using a quantitative assessment engine. The system then applies a readability score to the body of text based on the average complexity scores of the n-grams.

Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate language independent-speaker verification. In one aspect, a method includes actions of receiving, by a user device, audio data representing an utterance of a user. Other actions may include providing, to a neural network stored on the user device, input data derived from the audio data and a language identifier. The neural network may be trained using speech data representing speech in different languages or dialects. The method may include additional actions of generating, based on output of the neural network, a speaker representation and determining, based on the speaker representation and a second representation, that the utterance is an utterance of the user. The method may provide the user with access to the user device based on determining that the utterance is an utterance of the user.

Abstract: Systems and processes for operating an intelligent automated assistant to provide media items based on phonetic matching techniques are provided. An example method includes receiving a speech input from a user and determining whether the speech input includes a user request for a media item. The method further includes, in accordance with a determination that the speech input includes a user request for obtaining a media item, determining a candidate media item from a plurality of media items. The method further includes determining, based on a difference between a phonetic representation of the candidate media item and a phonetic representation of the speech input, whether the candidate media item is to be provided to the user. The method further includes, in accordance with a determination that the candidate media item is to be provided to the user, providing the candidate media item to the user.

Abstract: An apparatus and method for verifying voice messages generated by notification devices in an emergency address system includes one or more verification devices and a validation module, which can be part of a control panel or a connected services system. The verification devices can be mobile computing devices or permanently installed devices associated with each notification device in the emergency address system. The verification devices include microphones, network interfaces, and controllers executing speech to text conversion processes. During testing, the notification devices play voice messages and the verification devices detect the messages, convert the messages to text and send the text-converted messages to the validation module, which validates the text-converted messages against the intended messages for each notification device and confirms that the messages were played in the correct locations.

Abstract: An acoustic model is adapted, relating acoustic units to speech vectors. The acoustic model comprises a set of acoustic model parameters related to a given speech factor. The acoustic model parameters enable the acoustic model to output speech vectors with different values of the speech factor. The method comprises inputting a sample of speech which is corrupted by noise; determining values of the set of acoustic model parameters which enable the acoustic model to output speech with said first value of the speech factor; and employing said determined values of the set of speech factor parameters in said acoustic model. The acoustic model parameters are obtained by obtaining corrupted speech factor parameters using the sample of speech, and mapping the corrupted speech factor parameters to clean acoustic model parameters using noise characterization paramaters characterizing the noise.

Abstract: In one example, an assistant support server may maintain a web portal to crowdsource responses to a user input. The assistant support server may maintain a web portal accessible by a developer device. The assistant support server may store an assistant rule based on a developer input associating an input word set describing a hypothetical user input with a deep link for a website. The assistant support server may receive in the web portal the developer input. The assistant support server may direct a smart assistant module executed by a user device to connect to the deep link in response to receiving a user input from the smart assistant module matching the input word set.

Abstract: Systems and methods are provided to implement and facilitate cross-fading, interstitials and other effects/processing of two or more media elements in a personalized media delivery service. Effects or crossfade processing can occur on the broadcast, publisher or server-side, but can still be personalized to a specific user, in a manner that minimizes processing on the downstream side or client device. The cross-fade can be implemented after decoding, processing, re-encoding, and rechunking the relevant chunks of each component clip. Alternatively, the cross-fade or other effect can be implemented on the relevant chunks in the compressed domain, thus obviating any loss of quality by re-encoding. A large scale personalized content delivery service can limit the processing to essentially the first and last chunks of any file, there being no need to process the full clip.

Abstract: Approaches presented herein enable assignment of translated work to an agent in a support environment based on a confidence factor that measures accuracy of translation and an agent's language skill. Specifically, agent proficiencies in a set of natural languages are measured and scored. An incoming communication is translated into one or more natural languages and each language translation is assigned a translation score based on a confidence of translation. The skill score and translation score are utilized to calculate a confidence factor for each language. In one approach, the communication is assigned to an agent that has a confidence factor greater than a predetermined threshold confidence factor. In another approach, the communication is only assigned if a rule optimizing agent availability and risk of constrained resources is satisfied.

Abstract: A method is implemented to move media content display between two media output devices. A server system determines in a voice message recorded by an electronic device a media transfer request that includes a user voice command to transfer media content to a destination media output device and a user voice designation of the destination media output device. The server system then obtains from a source cast device instant media play information including information of a media play application, the media content that is being played, and a temporal position. The server system further identifies a destination cast device associated in a user domain coupled to the destination media output device, and sends to the destination cast device a media play request including the instant media play information, thereby enabling the destination cast device to execute the media play application for playing the media content from the temporal location.

Abstract: Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include updating a start state based rejection model and a key phrase model based on scores of sub-phonetic units from an acoustic model to generate a rejection likelihood score and a key phrase likelihood score and determining whether received audio input is associated with a predetermined key phrase based on the rejection likelihood score and the key phrase likelihood score.

Abstract: A data input system is described which has a user interface which receives one or more context text items in a sequence of text items input by a user. A processor of the data input system uses a plurality of language models to predict, from each language model, a next item in the sequence of text items. The processor uses a dynamic model which is bespoke to the user as a result of learning text items which the user has previously used, to predict a next item in the sequence of text items. The processor weights the predicted next item from the dynamic model using at least per term weights, each per term weight representing a likelihood of an associated term of the dynamic model given one of the language models.

Abstract: The present disclosure generally relates to systems and processes for emoji word sense disambiguation. In one example process, a word sequence is received. A word-level feature representation is determined for each word of the word sequence and a global semantic representation for the word sequence is determined. For a first word of the word sequence, an attention coefficient is determined based on a congruence between the word-level feature representation of the first word and the global semantic representation for the word sequence. The word-level feature representation of the first word is adjusted based on the attention coefficient. An emoji likelihood is determined based on the adjusted word-level feature representation of the first word. In accordance with the emoji likelihood satisfying one or more criteria, an emoji character corresponding to the first word is presented for display.

Abstract: An information processing system that that confirms the meanings of difference information in meeting content with reference to the sound information is provided. Differences between meeting content contained in image information of a paper medium taken at each detection cycle and meeting content contained in master information are extracted. Surrounding sounds are recorded while the meeting is being held. The sound information of the recorded sounds is associated with the difference information of the extracted differences and also associated with the master information with the timing when the differences of the meeting content are detected.

Abstract: Systems and methods associated with pagination point identification are disclosed. One example system includes an interface logic. The interface logic may receive a content element to be arranged within a layout having a first page with a fixed size. The system also includes a pagination logic. The pagination logic may identify a pagination point within a content element based on semantic information from the content element. The system also includes a layout logic. The layout logic may arrange a portion of the content element within the first page based on the pagination point and the fixed size.

Abstract: The present disclosure relates to remote service requesting and processing. The method includes: receiving a service processing request sent by a terminal; recognizing voice data in the service processing request to obtain voice recognition information; and sending the voice recognition information and an Internet application identifier to a corresponding third-party server according to a public identifier, so that the third-party server processes a corresponding service according to the voice recognition information. The voice data in the service processing request sent by the terminal is recognized to obtain the voice recognition information. The voice recognition information and the Internet application identifier are sent to the third-party server, so that the third-party server processes the corresponding service according to the voice recognition information.

Abstract: A system, method and computer-readable storage devices are disclosed for multi-modal interactions with a system via a long-touch gesture on a touch-sensitive display. A system operating per this disclosure can receive a multi-modal input comprising speech and a touch on a display, wherein the speech comprises a pronoun. When the touch on the display has a duration longer than a threshold duration, the system can identify an object within a threshold distance of the touch, associate the object with the pronoun in the speech, to yield an association, and perform an action based on the speech and the association.

Abstract: When combining digital data sets in the time domain into a combined digital data set a subset of samples of each digital data set is adjusted to enable unraveling the data when decoding. To enable correction during decoding of an error introduced by the adjustment, an error approximation is stored for each adjusted sample. A set of error approximations is created which is indexed allowing substantial reduction in size of the error approximations to be stored for the adjusted samples. Instead of creating a set of error approximations for each combined digital data set one set of error approximations is created based on the errors introduced when creating multiple combined digital data sets.