Abstract: A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

Abstract: A method and apparatus of sharing documents during a conference call data is disclosed. One example method may include initiating a document sharing operation during a conference call conducted between at least two participants communicating during the conference call. The method may also include transferring the document from one of the two participants to another of the two participants, and recording at least one action performed to the document by the participants during the conference call.

Abstract: A system and method of processing disfluent speech at an automatic speech recognition (ASR) system includes: receiving speech from a speaker via a microphone; determining the received speech includes disfluent speech; accessing a disfluent speech grammar or acoustic model in response to the determination; and processing the received speech using the disfluent speech grammar.

Abstract: Sound rate modification techniques are described. In one or more implementations, an indication is received of an amount that a rate of output of sound data is to be modified. One or more sound rate rules are applied to the sound data that, along with the received indication, are usable to calculate different rates at which different portions of the sound data are to be modified, respectively. The sound data is then output such that the calculated rates are applied.

Abstract: Methods, systems and program product are disclosed for determining matching level of a text lookup segment with a plurality of source texts in a translation memory in terms of context. The invention determines exact matches for the lookup segment in the plurality of source texts, and determines, in the case that at least one exact match is determined, that a respective exact match is an in-context exact match for the lookup segment in the case that a context of the lookup segment matches that of the respective exact match. Degree of context matching required can be predetermined, and results prioritized. The invention also includes methods, systems and program products for storing a translation pair of source text and target text in a translation memory including context, and the translation memory so formed. The invention ensures that content is translated the same as previously translated content and reduces translator intervention.

Abstract: The invention relates to a human-machine dialogue device (1), characterized in that it comprises: a housing comprising a docking station having: a universal human-machine dialogue assembly, each universal human-machine dialogue assembly comprising at least one display unit and at least one sensor device, a universal actuation device, the docking station being arranged to receive, without distinction, removably and interchangeably: a first modular unit (2c) having a display interface, a second modular unit (2a) having a pushbutton-type control interface, a third modular unit (2b) having a rotary button-type control interface.

Abstract: A computer-implemented technique is described for processing a linguistic item (e.g., a query) in an efficient and scalable manner. The technique interprets the linguistic item using a language understanding (LU) system in a manner that is based on a particular endpoint mechanism from which the linguistic item originated. The LU system may include an endpoint-independent subsystem, an endpoint-dependent subsystem, and a ranking component. The endpoint-independent subsystem interprets the linguistic item in a manner that is independent of the particular endpoint mechanism. The endpoint-dependent subsystem interprets the linguistic item in a manner that is dependent on the particular endpoint mechanism. The ranking component generates final interpretation results based on intermediate results generated by the endpoint-independent subsystem and the endpoint-dependent subsystem, e.g., by identifying the most likely interpretation of the linguistic item.

Abstract: A third-party company may assist companies in providing natural language interfaces for their customers. To implement a natural language interface for a company, a configuration may be received that includes information, such as a list intents, seed messages for the intents, and hierarchical information of the intents. An intent classifier may be trained using the configuration, and the natural language interface may be deployed for use with customers. Usage data of the natural language classifier may be collected and used to improve the natural language interface. Messages corresponding to an intent may be clustered into clusters of similar messages, and a prototype message may be obtained for each cluster to provide a human understandable description of the cluster. The information about the clusters may be used to improve the natural language interface, such as by creating a new intent with a cluster or moving a cluster to a different intent.

Abstract: A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

Abstract: The present disclosure provides an information entry method and a corresponding device. The method comprises: step a): acquiring in real-time motion data from a user companion device; step b): determining whether the device changes from a first motion status to a second motion status based on the motion data; if so, activating a recording module of the device; step c): recording in real-time the user's voice input through the recording module; step d): stopping recording according to a preset voice instruction of stopping recording. The method and device can address a need of information entry in the following scenario: when a user incidentally wants to record some audios during running or trotting, the device may quickly activate its own recording module based on the acquired motion data so as to enter information in an audio manner, without performing a touch operation on the companion device.

Abstract: A decoder for generating a frequency enhanced audio signal, includes: a feature extractor for extracting a feature from a core signal; a side information extractor for extracting a selection side information associated with the core signal; a parameter generator for generating a parametric representation for estimating a spectral range of the frequency enhanced audio signal not defined by the core signal, wherein the parameter generator is configured to provide a number of parametric representation alternatives in response to the feature, and wherein the parameter generator is configured to select one of the parametric representation alternatives as the parametric representation in response to the selection side information; and a signal estimator for estimating the frequency enhanced audio signal using the parametric representation selected.

Abstract: A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

Abstract: Natural speech dialog system and methods are disclosed. In one example, a method includes identifying a dialog system intent associated with the speech input based on at least one predetermined intent keyword, the dialog system intent having required intent parameters, determining whether data for all required intent parameters of the dialog system are available, based on the determination, selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required parameters not otherwise available to the dialog system intent, and based on the dialog system intent and one or more required parameters, generating an action instruction.

Abstract: The present invention proposes a new method for improving the performance of a real-valued filterbank based spectral envelope adjuster. By adaptively locking the gain values for adjacent channels dependent on the sign of the channels, as defined in the application, reduced aliasing is achieved. Furthermore, the grouping of the channels during gain-calculation, gives an improved energy estimate of the real valued subband signals in the filterbank.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, audio data that corresponds to an utterance. The actions further include determining a first value corresponding to a likelihood that the utterance includes a hotword. The actions further include receiving a second value corresponding to a likelihood that the utterance includes the hotword, the second value being determined by a second computing device. The actions further include comparing the first value and the second value. The actions further include based on comparing the first value to the second value, initiating speech recognition processing on the audio data.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: A computing system is operable as virtual personal assistant (VPA) to understand relationships between different instances of natural language dialog expressed by different people in a multi-person conversational dialog session. The VPA can develop a common resource, a shared intent, which represents the VPA's semantic understanding of at least a portion of the multi-person dialog experience. The VPA can store and manipulate multiple shared intents, and can alternate between different shared intents as the multi-person conversation unfolds. With the shared intents, the computing system can generate useful action items and present the action items to one or more of the participants in the dialog session.

Abstract: A method for explaining a form that includes receiving input code, wherein the input code is associated with the form, processing the input code to create an explanation dynamically associated with the form, and outputting the explanation into a natural language.

Abstract: In one embodiment, the method includes receiving an audio data frame having at least first and second channels. The first and second channels are synchronously subdivided into blocks such that the lengths of the blocks into which the second channel is subdivided correspond to the lengths of the blocks into which the first channel is subdivided if the first and second channels are correlated with each other and difference coding is used. The first and second channels are decoded and the subdivided blocks of the first and second channels are interleaved if the first and second channels are synchronously subdivided.

Abstract: In one embodiment, at least first and second channels in a frame of the audio signal are independently subdivided into blocks if the first and second channels are not correlated with each other. At least two of the blocks have different block lengths. Furthermore, the first and second channels are correspondingly subdivided into blocks such that the lengths of the blocks into which the second channel is subdivided correspond to the lengths of the blocks into which the first channel is subdivided if the first and second channels are correlated with each other. At least two of the blocks have different block lengths.