Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: Systems and methods for proactively assisting users with accurately locating a parked vehicle are disclosed herein. An example method includes: automatically, and without instructions from a user: determining that a user of the electronic device is in a vehicle that has come to rest at a geographic location. Upon determining that the user has left the vehicle at the geographic location, the method includes automatically, and without instructions from a user: determining whether positioning information, retrieved from the location sensor to identify the geographic location, satisfies accuracy criteria. Upon determining that the positioning information does not satisfy the accuracy criteria, the method includes: providing a prompt to the user to input information about the geographic location. In response to providing the prompt, the method includes receiving information from the user about the geographic location and storing the information as vehicle location information.

Abstract: Systems and methods for proactively populating an application with information that was previously viewed by a user in a different application are disclosed herein. An example method includes: while displaying a first application, obtaining information identifying a first physical location viewed by a user in the first application. The method also includes exiting the first application and, after exiting the first application, receiving a request from the user to open a second application that is distinct from the first application. In response to receiving the request and in accordance with a determination that the second application is capable of accepting geographic location information, the method includes presenting the second application so that the second application is populated with information that is based at least in part on the information identifying the first physical location.

Abstract: Systems and processes for detecting an event within natural language are provided. In one example of a process, unstructured natural language information may be received from at least one user. The presence of event information in the unstructured natural language information may be determined. In accordance with a determination that event information is present within the unstructured natural language information, a pseudo-event entry associated with that event information may be generated.

Abstract: Systems and processes for language identification from short strings are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving user input including an n-gram and determining a similarity between a representation of the n-gram and a representation of a first language. The representation of the first language is based on an occurrence of each of a plurality of n-grams in the first language and an occurrence of each of the plurality of n-grams in a second language. The method further includes determining whether the similarity between the representation of the n-gram and the representation of the first language satisfies a threshold.

Abstract: A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated.

Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: Exemplary embodiments of methods and apparatuses for automatic speech recognition are described. First model parameters associated with a first representation of an input signal are generated. The first representation of the input signal is a discrete parameter representation. Second model parameters associated with a second representation of the input signal are generated. The second representation of the input signal includes a continuous parameter representation of residuals of the input signal. The first representation of the input signal includes discrete parameters representing first portions of the input signal. The second representation includes discrete parameters representing second portions of the input signal that are smaller than the first portions. Third model parameters are generated to couple the first representation of the input signal with the second representation of the input signal. The first representation and the second representation of the input signal are mapped into a vector space.

Abstract: Systems and processes for natural language processing are provided. In accordance with one example, a method includes, at a first electronic device with one or more processors and memory, receiving a plurality of words, mapping each of the plurality of words to a word representation, and associating the mapped words to provide a plurality of phrases. In some examples, each of the plurality of phrases has a representation of a first type. The method further includes encoding each of the plurality of phrases to provide a respective plurality of encoded phrases. In some examples, each of the plurality of encoded phrases has a representation of a second type different than the first type. The method further includes determining a value of each of the plurality of encoded phrases and identifying one or more phrases of the plurality of encoded phrases having a value exceeding a threshold.

Abstract: Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

Abstract: Systems and methods are disclosed for predicting words using a structured stem and suffix n-gram language model. The systems and methods include determining, using a first n-gram word language model, a first probability of a stem based on a first portion of a previously-input word in the received input. Using a second n-gram language model, a second probability of a first suffix may be determined based at least on a second portion the previously-input word in the received input. Further, a third probability of a second suffix different from the first suffix may be determined using a third n-gram language model based at least on a third portion of the previously-input word in the received input. A fourth probability of a predicted word may be determined based on the first, second and third probabilities. One or more predicted words may be determined and provided as an output to the user.

Abstract: Differing embodiments of this disclosure may employ one or all of the several techniques described herein to perform credit card recognition using electronic devices with integrated cameras. According to some embodiments, the credit card recognition process may comprise: obtaining a first representation of a first image, wherein the first representation comprises a first plurality of pixels; identifying a first credit card region within the first representation; extracting a first plurality of sub-regions from within the identified first credit card region, wherein a first sub-region comprises a credit card number, wherein a second sub-region comprises an expiration date, and wherein a third sub-region comprises a card holder name; generating a predicted character sequence for the first, second, and third sub-regions; and validating the predicted character sequences for at least the first, second, and third sub-regions using various credit card-related heuristics, e.g.

Abstract: Exemplary embodiments of methods and apparatuses for automatic speech recognition are described. First model parameters associated with a first representation of an input signal are generated. The first representation of the input signal is a discrete parameter representation. Second model parameters associated with a second representation of the input signal are generated. The second representation of the input signal includes a continuous parameter representation of residuals of the input signal. The first representation of the input signal includes discrete parameters representing first portions of the input signal. The second representation includes discrete parameters representing second portions of the input signal that are smaller than the first portions. Third model parameters are generated to couple the first representation of the input signal with the second representation of the input signal. The first representation and the second representation of the input signal are mapped into a vector space.

Abstract: Systems and processes are disclosed for predicting words using a categorical stem and suffix word n-gram language model. A word prediction includes determining a stem probability using a stem language model. The word prediction also includes determining a suffix probability using suffix language model decoupled from the stem model, in view of one or more stem categories. The word prediction also includes determine a probability of the stem belonging to the stem category. A joint probability is determined based on the foregoing, and one or more word predictions having sufficient likelihood. In this way, the categorical stem and suffix language model constraints predicted suffixes to those that would be grammatically valid with predicted stems, thereby producing word predictions with grammatically valid stem and suffix combinations.

Abstract: Systems and processes for discourse input processing are provided. In one example process, a discourse input can be received from a user. An integrated probability of a candidate word in the discourse input and one or more subclasses associated with the candidate word can be determined based on a conditional probability of the candidate word given one or more words in the discourse input, a probability of the candidate word within a corpus, and a conditional probability of the candidate word given one or more classes associated with the one or more words. A text string corresponding to the discourse input can be determined based on the integrated probability. An output based on the text string can be generated.

Abstract: A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker-specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated.

Abstract: Systems and processes are disclosed for predicting words in a text entry environment. Candidate words and probabilities associated therewith can be determined by combining a word n-gram language model and a character m-gram language model. Based on entered text, candidate word probabilities from the word n-gram language model can be integrated with the corresponding candidate character probabilities from the character m-gram language model. A reduction in entropy can be determined from integrated candidate word probabilities before entry of the most recent character to integrated candidate word probabilities after entry of the most recent character. If the reduction in entropy exceeds a predetermined threshold, candidate words with high integrated probabilities can be displayed or otherwise made available to the user for selection. Otherwise, displaying candidate words can be deferred (e.g., pending receipt of an additional character from the user leading to reduced entropy in the candidate set).

Abstract: Differing embodiments of this disclosure may employ one or all of the several techniques described herein to perform credit card recognition using electronic devices with integrated cameras. According to some embodiments, the credit card recognition process may comprise: obtaining a first representation of a first image, wherein the first representation comprises a first plurality of pixels; identifying a first credit card region within the first representation; extracting a first plurality of sub-regions from within the identified first credit card region, wherein a first sub-region comprises a credit card number, wherein a second sub-region comprises an expiration date, and wherein a third sub-region comprises a card holder name; generating a predicted character sequence for the first, second, and third sub-regions; and validating the predicted character sequences for at least the first, second, and third sub-regions using various credit card-related heuristics, e.g.

Abstract: Differing embodiments of this disclosure may be employed to perform character sequence recognition with no explicit character segmentation.

Abstract: A first technique of recognizing content is disclosed, including: determining a first value representative of a pixel content present at a first set of pixels associated with a first distance from a pixel under consideration; determining a second value representative of a pixel content present at a second set of pixels associated with a second distance from the pixel under consideration; and using the first and second values to compute one or more spatial features associated with the pixel under consideration for purposes of content recognition. A second technique of recognizing content is also disclosed, including: determining, for a pixel, a first value representative of a first feature associated with a set of pixels associated with a first direction from the pixel; and determining, for the pixel, a second value representative of a second feature associated with a set of pixels associated with a second direction from the pixel.