Abstract: Provided are a voice audio encoding device, voice audio decoding device, voice audio encoding method, and voice audio decoding method that efficiently perform bit distribution and improve sound quality. Dominant frequency band identification unit identifies a dominant frequency band having a norm factor value that is the maximum value within the spectrum of an input voice audio signal. Dominant group determination units and non-dominant group determination unit group all sub-bands into a dominant group that contains the dominant frequency band and a non-dominant group that contains no dominant frequency band. Group bit distribution unit distributes bits to each group on the basis of the energy and norm variance of each group. Sub-band bit distribution unit redistributes the bits that have been distributed to each group to each sub-band in accordance with the ratio of the norm to the energy of the groups.

Abstract: Systems and methods are disclosed for creating a machine generated avatar. A machine generated avatar is an avatar generated by processing video and audio information extracted from a recording of a human speaking a reading corpora and enabling the created avatar to be able to say an unlimited number of utterances, i.e., utterances that were not recorded. The video and audio processing consists of the use of machine learning algorithms that may create predictive models based upon pixel, semantic, phonetic, intonation, and wavelets.

Abstract: A topic providing device includes a candidate topic extractor, a provided topic determiner, a voice synthesizer, and a speaker. When a determination is made that a parent and child are conversing and that there is a need to provide a new topic to the parent and child, based on a conversation history database and a child activity database storing at least one activity name indicating an activity the child was engaged in for a first predetermined period of time, the candidate topic extractor extracts at least one candidate topic that corresponds to the at least one activity name in the child activity database and does not correspond to an activity name included in text data recorded in a first database. From the at least one candidate topic, the provided topic determiner selects one topic to provide to the parent and the child. The voice synthesizer generates voice data containing the one topic. The speaker outputs the voice data.

Abstract: Embodiments of this disclosure disclose a voice interaction based method and apparatus for generating a multimedia playlist. An embodiment of the method comprises: acquiring first voice request information for playing multimedia resources; identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information; finding the multimedia resources having the key tag in a multimedia resource library; and generating a multimedia playlist based on the found multimedia resources. The embodiment realizes automatic generation of multimedia playlists and improves the efficiency of voice service.

Abstract: There is provided a system in which empowerment is performed by outputting conversation information to the user, the system including: a computer including a processor, a memory, and an interface; and a measuring device that measures signals of a plurality of types, wherein the processor calculates values of conversation parameters of a plurality of attributes for evaluating a state of a user who performs the empowerment on the basis of a plurality of signals measured by the measuring device, the processor selects a selection parameter which is a conversation parameter of a change target on the basis of the values of the conversation parameters of the plurality of attributes, the processor decides conversation information for changing a value of the selection parameter, and the processor outputs the decided conversation information to the user.

Abstract: The present disclosure provides a speech recognition method and device based on artificial intelligence. The method includes: collecting signals of an array of microphones to obtain a plurality of first speech signals; filtering out a reverberation signal in each first speech signal to obtain a plurality of second speech signals, and obtaining a third speech signal based on the plurality of second speech signals; performing noise extraction on each first speech signal based on the third speech signal to obtain a plurality of first noise signals; and filtering and adding the plurality of first noise signals to obtain a second noise signal, and subtracting the second noise signal from the third speech signal to obtain a target speech signal.

Abstract: A system, method and computer program product for cognitive copy and paste. The method includes: receiving, at a hardware processor of a computer system, an input representing a selection of a content captured from a source application program, and receiving an input representing an identified target application program that will receive the selected content to be copied and rendered in the target application program. The selected content is analyzed to determine a context for the selected content; and a rendering of the selected content at a location within the destination application based on the determined context, the rendering achieving a best representation of the selected content on the destination application. The analyzing includes invoking a natural language processor to determine an intent, meaning, or an intended use of the selected content based on the determined context, and employs a support vector machine for determining a best format change when rendering.

Abstract: A mistranscription generated by a speech recognition system is identified. A first class of utterance members is provided for use by the speech recognition system, each utterance class member consisting of a respective number of words. The first class is defined by a first common meaning and a first common system response if a class member of the first class is recognized. If the speech recognition system matches a received utterance to a first class member of the first class, the received utterance is sent to a mistranscription analyzer. The received utterance contains a mistranscription as compared to the first class member. Evidence is incremented by the mistranscription analyzer that the received utterance is evidence of the mistranscription of the first class member. If the incremented evidence for the mistranscription of the first class member exceeds a first threshold, a second class member is added to the first class of utterance members based on the mistranscription of the first class member.

Abstract: A method of processing an audio signal, according to an embodiment of the present invention for solving the technical problem, further includes: receiving a signal for one channel pair element (CPE) to which internal channel gains (ICGs) have been pre-applied; when a reproduction channel configuration is not stereo, acquiring inverse ICGs for the one CPE based on Motion Picture Experts Group surround 212 (MPS212) parameters and on rendering parameters corresponding to MPS212 output channels defined in a format converter; and generating output signals based on the received signal for the one CPE and the acquired inverse ICGs.

Abstract: In one aspect, a first device includes a processor and storage accessible to the at least one processor. The storage bears instructions executable by the processor to execute a digital assistant, receive input for the digital assistant to perform a task, determine the task indicated in the input, determine whether to use a second device for processing the input based on the determination of the task at the first device, and transmit at least a portion of the input to the second device. The instructions are also executable by the processor to, responsive to a determination to not use the second device for processing the input, execute the task at the first device and using the digital assistant without receiving a response from the second device.

Abstract: A system, method and computer program product for cognitive copy and paste. The method includes: receiving, at a hardware processor of a computer system, an input representing a selection of a content captured from a source application program, and receiving an input representing an identified target application program that will receive the selected content to be copied and rendered in the target application program. The selected content is analyzed to determine a context for the selected content; and a rendering of the selected content at a location within the destination application based on the determined context, the rendering achieving a best representation of the selected content on the destination application. The analyzing includes invoking a natural language processor to determine an intent, meaning, or an intended use of the selected content based on the determined context, and employs a support vector machine for determining a best format change when rendering.

Abstract: A mistranscription generated by a speech recognition system is identified. A set of known utterance members is provided for use by a speech recognition system. Each utterance member consists of a respective plural number of words. A received utterance is matched to a first utterance member within the set of known utterance members. The first utterance member is a closest matching utterance member and has a first plural number of words. The matching operation matches fewer than the first plural number of words in the received utterance and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member. The received utterance is sent to a mistranscription analyzer component which increments evidence that the received utterance is evidence of a mistranscription.

Abstract: A voice recognition system includes a server storing a plurality of manuals and a display apparatus transmitting, when a spoken voice of a user is recognized, characteristic information and a spoken voice signal corresponding to the spoken voice to the server, the characteristic information is characteristic information of the display apparatus, the server transmits a response signal to the spoken voice signal to the display apparatus based on a manual corresponding to the characteristic information among the plurality of manuals, and the display apparatus processes an operation corresponding to the received response signal; as a result, user convenience increases.

Abstract: Devices and techniques are generally described for control of a voice-controlled device using acoustic echo cancellation statistics. A reference signal representing the audio stream may be sent to an acoustic echo cancellation (AEC) unit. A microphone may receive an input audio signal and send the input audio signal to the AEC unit. The AEC unit may attenuate at least a part of the input audio signal. AEC statistics related to the attenuation of at least the part of the input audio signal may be determined over a first period of time. A wake-word in the input audio signal may be detected during the first period of time. A determination may be made that the wake-word is part of the playback of the audio stream based at least in part on the AEC statistics.

Abstract: A framework for annotating image edit requests includes a structure for identifying natural language request as either comments or image edit requests and for identifying the text of a request that maps to an executable action in an image editing program, as well as to identify other entities from the text related to the action. The annotation framework can be used to aid in the creation of artificial intelligence networks that carry out the requested action. An example method includes displaying a test image, displaying a natural language input with selectable text, and providing a plurality of selectable action tag controls and entity tag controls. The method may also include receiving selection of the text, receiving selection of an action tag control for the selected text, generating a labeled pair, and storing the labeled pair with the natural language input as an annotated natural language image edit request.

Abstract: The disclosure generally describes computer-implemented methods, software, and systems for self-learning localization services. A computer-implemented method includes: identifying, at a location remote from a first application, a request for localization of a string value associated with the first application from a source language to a target language, sending the string value to a translation request buffer in response to a determination that the localization of the string value in the target language is unavailable, and triggering, in response to satisfaction of at least one heuristic analysis, a translation process of the string value from the source language into the target language where the string value is retrieved from the translation request buffer. In some instances, the location remove from the first application is a centralized localization service accessible by remote requests from a plurality of applications.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

Abstract: An echo cancellation system that synchronizes output audio data with input audio data in a heterogeneous system. The system may append a most recent outgoing audio data frame to an incoming audio data frame to synchronize a receiving buffer with a transmission buffer. By synchronizing the receiving buffer with the transmission buffer, the incoming audio data frames may be associated with corresponding outgoing audio data frames. After synchronizing the incoming audio data frames and the outgoing audio data frames, the system may perform Acoustic Echo Cancellation by removing the outgoing audio data frames from the incoming audio data frames.

Abstract: A method is provided for analyzing and interpreting a dataset composed of electronic documents including free-form text. The method includes text mining the documents for terms of interest, including receiving a set of seed nouns as input to an iterative process an iteration of which includes searching for multiword terms having seed nouns as their head words, at least some of which define a training set of a machine learning algorithm used to identify additional multiword terms at least some of which have nouns outside the set of seed nouns as their head words. The iteration also includes adding the nouns outside the set of seed nouns to the set and thereby identifying a new set of seed nouns for a next iteration. The method includes unifying terms of interest to produce normalized terms of interest for application to generate features of the documents for data analytics performed thereon.

Abstract: Network connected devices are controlled. A command is received. A graph model is applied to identify a subset of nodes related to the command. The graph model includes a plurality of nodes that each correspond to a device and the graph model includes a plurality of edges that specify relationships between the plurality of nodes. The subset of nodes is activated in response to the command.