Abstract: Disclosed are an electronic apparatus and a voice recognition method for the same. The voice recognition method for the electronic apparatus includes: receiving an input voice of a user; determining characteristics of the user; and recognizing the input voice based on the determined characteristics of the user.

Abstract: In encoding, pitch periods for time series signals in a predetermined time interval are calculated, and a code corresponding thereto is output. In that encoding, the resolutions for expressing the pitch periods and/or a pitch period encoding mode are switched according to whether an index indicating a periodicity and/or stationarity level of the time series signals satisfies a condition indicating high or low in periodicity and/or stationarity. In that decoding, according to whether an index indicating a periodicity and/or stationarity level, the index being included in or obtained from an input code corresponding to the predetermined time interval, satisfies a condition indicating high periodicity and/or stationarity, a decoding mode for a code, included in the input code, corresponding to pitch periods is switched to decode the code corresponding to the pitch periods to obtain the pitch periods corresponding to the predetermined time interval.

Abstract: In encoding, pitch periods for time series signals in a predetermined time interval are calculated, and a code corresponding thereto is output. In that encoding, the resolutions for expressing the pitch periods and/or a pitch period encoding mode are switched according to whether an index indicating a periodicity and/or stationarity level of the time series signals satisfies a condition indicating high or low in periodicity and/or stationarity. In that decoding, according to whether an index indicating a periodicity and/or stationarity level, the index being included in or obtained from an input code corresponding to the predetermined time interval, satisfies a condition indicating high periodicity and/or stationarity, a decoding mode for a code, included in the input code, corresponding to pitch periods is switched to decode the code corresponding to the pitch periods to obtain the pitch periods corresponding to the predetermined time interval.

Abstract: In encoding, pitch periods for time series signals in a predetermined time interval are calculated, and a code corresponding thereto is output. In that encoding, the resolutions for expressing the pitch periods and/or a pitch period encoding mode are switched according to whether an index indicating a periodicity and/or stationarity level of the time series signals satisfies a condition indicating high or low in periodicity and/or stationarity. In that decoding, according to whether an index indicating a periodicity and/or stationarity level, the index being included in or obtained from an input code corresponding to the predetermined time interval, satisfies a condition indicating high periodicity and/or stationarity, a decoding mode for a code, included in the input code, corresponding to pitch periods is switched to decode the code corresponding to the pitch periods to obtain the pitch periods corresponding to the predetermined time interval.

Abstract: The present invention includes systems and methods for sending social media messages without the need for keyboard inputs. A microphone captures live audio speech data and transmits the audio data to a processing unit. The processing unit converts the audio to speech data. The processing unit also removes censored words, emphasizes key words, and edits that data to include product and promotional messages where appropriate. The processing unit then uses code words contained in the speech data to send the speech data to the appropriate social media outlets for output.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting various word data from cross-domain sources and subject websites; assessing relevancy of feature vectors from external domains, live content of subject websites, and secondary terms derived from the live contents; expanding a language model for a domain by relevance passing a logistic regression threshold.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: determining that one or more word of a feature vector more supports than negates a language model corresponding to the domain based on a sensitivity of respective word. Words having acceptable sensitivities are added to the language model, and the language model is enhanced by use of machine learning in order to accurately and comprehensively model the language specific for the domain.

Abstract: A system extracting features from a time-varying signal comprising a computer processor and a computer readable medium having computer executable instructions for providing: a bank of bandpass filters; a module approximating the output of those filters with nonlinear components; a module representing a decorrelated projection of the output of the filters with nonlinear components; and a module representing the temporal derivative of the decorrelated information with nonlinear components.

Abstract: Techniques are described for modeling information from a data source. In one example, a method for modeling information from a data source includes comparing, with one or more computing devices, a data item heading from the data source with concept keywords in a concept library, the concept library comprising a plurality of concepts and one or more of the concept keywords in at least one language associated with each of one or more of the concepts. The method further includes identifying, with one or more computing devices, one or more matches between the data item heading and one or more concept keywords associated with a particular concept from among the concepts comprised in the concept library. The method further includes identifying, with one or more computing devices, the data item heading as being associated with the particular concept.

Abstract: A system for dynamically adjusting a voice recognition system is provided herein. The system employs a methodology for determining a display associated with a disambiguation window, with the determination employing a detection system scoring to display disambiguation based on the vocal clarity of the speaker and other environmental factors that may affect detection.

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 audio data that corresponds to an utterance. The actions further include determining that the utterance likely includes a particular, predefined hotword. The actions further include transmitting (i) data indicating that the computing device likely received the particular, predefined hotword, (ii) data identifying the computing device, and (iii) data identifying a group of nearby computing devices that includes the computing device. The actions further include receiving an instruction to commence speech recognition processing on the audio data. The actions further include in response to receiving the instruction to commence speech recognition processing on the audio data, processing at least a portion of the audio data using an automated speech recognizer on the computing device.

Abstract: There is provided a system and a method for detecting meaningless lexical units in a text message, the method comprising: performing a syntax analysis of the text message and determining at least one lexical unit as a first potential meaningless lexical unit; determining a control sum of the first potential meaningless lexical unit; matching using a first parameter, the first potential meaningless lexical unit with lexical units from a plurality of lexical units from a lexical units database, wherein matching using the first parameter comprises matching a control sum of the first potential meaningless lexical unit with control sums of meaningless lexical units from the lexical units database; determining the first potential meaningless lexical unit is a meaningless lexical unit if the lexical units database includes at least one meaningless lexical unit with a control sum corresponding to the control sum of the first potential meaningless lexical unit.

Abstract: Various embodiments describe a multi-step process for determining whether the keyword has been spoken. The first tier uses an onboard digital signal processor (DSP) to process converted audio signals. If the DSP analysis cannot confirm the keyword due to noise in the signal, a second tier of processing may use an applications processor (AP) and a more stringent audio filter to try to verify the keyword. If the AP analysis cannot confirm the keyword, a third tier of processing may use server side processor and an even more stringent audio filter to try to verify the keyword. Certain signal to noise ratios (SNRs) of the detected and converted audio signal are used to decide when and if to try the second and third tier of processing.

Abstract: The invention provides a computer system for interacting with a user. A set of concepts initially forms a target set of concepts. An input module receives a language input from the user. An analysis system executes a plurality of narrowing cycles until a concept packet having at least one concept has been identified. Each narrowing cycle includes identifying at least one portion of the language and determining a subset of concepts from the target set of concepts to form a new target subset. An action item identifier identifies an action item from the action items based on the concept packet. An action executer that executes an action based on the action item that has been identified.

Abstract: A decoder for generating an audio output signal having one or more audio output channels is provided, having a receiving interface for receiving an audio input signal having a plurality of audio object signals, for receiving loudness information on the audio object signals, and for receiving rendering information indicating whether one or more of the audio object signals shall be amplified or attenuated, further having a signal processor for generating the one or more audio output channels of the audio output signal, configured to determine a loudness compensation value depending on the loudness information and depending on the rendering information, and configured to generate the one or more audio output channels of the audio output signal from the audio input signal depending on the rendering information and depending on the loudness compensation value. One or more by-pass audio object signals are employed for generating the audio output signal. Moreover, an encoder is provided.

Abstract: Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user.

Abstract: An information analysis system includes a remark analysis unit, a thread analysis unit, and a storing unit. The remark analysis unit analyzes importance of a remark included in a thread serving as a group of remarks posted on a network, based on remark data serving as data relating to the remark, for each of the remarks. The thread analysis unit analyzes which of a plurality of preset categories the thread belongs to, based on thread data serving as data relating to the thread. The storing unit stores the remark, the importance of the remark, and a category of the thread including the remark in association with each other for each of the remarks, in a predetermined storage unit.

Abstract: The present disclosure relates to applying techniques similar to those used in neural network language modeling systems to a content recommendation system. For example, by associating consumed media content to words of a language model, the system may provide content predictions based on an ordering. Thus, the systems and techniques described herein may produce enhanced prediction results for recommending content (e.g. word) in a given sequence of consumed content. In addition, the system may account for additional user actions by representing particular actions as punctuation in the language model.

Abstract: A method is provided for detecting a predetermined frequency band in an audio data signal which has previously been coded according to a succession of data blocks, among which at least certain blocks contain respectively at least one set of spectral parameters representing a linear prediction filter. Such a method of detection implements, for a current block among the at least certain blocks and for which at least a plurality of spectral parameters of the set have been previously decoded, acts of: determining, among the plurality of previously decoded spectral parameters, the index of the first spectral parameter closest to a threshold frequency; calculating at least one criterion on the basis of the determined index; and deciding whether the predetermined frequency band is detected in the current block, as a function of the criterion calculated.

Abstract: A method for sending data to a user device comprises establishing a communicative connection between a first user device and a server, receiving the data at the first user device, caching the data on the first user device, establishing a communicative connection between the first user device and a second user device, determining whether the first user device is moving out of communicative range with the second user device, sending the data from the first user device to the second user device responsive to determining that the first user device is moving out of communicative range with the second user device, and caching the data on the second user device.