Abstract: Methods and systems are provided for generating automatic program recommendations based on user interactions. In some embodiment, control circuitry processes verbal data received during an interaction between a user of a user device and a person with whom the user is interacting. The control circuitry analyzes the verbal data to automatically identify a media asset referred to during the interaction by at least one of the user and the person with whom the user is interacting. The control circuitry adds the identified media asset to a list of media assets associated with the user of the user device. The list of media assets is transmitted to a second user device of the user.

Abstract: Disclosed is a method and apparatus for responding to an inquiry from a client via a network. The method and apparatus receive the inquiry from a client via a network. Based on the inquiry, question-answer pairs retrieved from the network are analyzed to determine a response to the inquiry. The QA pairs are not predefined. As a result, the QA pairs have to be analyzed in order to determine whether they are responsive to a particular inquiry. Questions of the QA pairs may be repetitive and similar to one another even for very different subjects, and without additional contextual and meta-level information, are not useful in determining whether their corresponding answer responds to an inquiry.

Abstract: In some implementations, a language proficiency of a user of a client device is determined by one or more computers. The one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. After determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. The audio data including the synthesized utterance of the text segment is then provided to the client device for output.

Abstract: The various implementations described herein include methods and systems for determining device leadership among voice interface devices. In one aspect, a method is performed at an electronic device that includes microphones, a speaker, processors, and memory storing one or more programs for execution by the one or more processors. The electronic device: (1) detects a voice input; (2) determines a first quality score for the detected voice input; (3) receives quality scores generated by other electronic devices for detection of the voice input by the other electronic devices; (4) in accordance with a determination that the first quality score is not the highest amongst the quality scores for the voice input, identifies a criterion associated with the voice input; and (5) in accordance with a determination that the identified criterion is the most relevant to the electronic device, responds to the detected input.

Abstract: A method of processing received data representing speech comprises monitoring the received data to detect the presence of data representing a first portion of a trigger phrase in said received data. On detection of the data representing the first portion of the trigger phrase, a control signal is sent to activate a speech processing block. The received data is monitored to detect the presence of data representing a second portion of the trigger phrase in said received data. If the control signal to activate the speech processing block has previously been sent, then, on detection of the data representing the second portion of the trigger phrase, the activation of the speech processing block is maintained.

Abstract: A method and device for determining semantic similarity between two character strings are disclosed. The two character strings are segmented into sequences of words or phrases which represent the correlation between the characters. Edit distance from the first sequence to the second sequence is calculated based on a predetermined algorithm. A minimum semantic distance is then determined from the edit distance by considering the word/phrase pairs appearing in both sequences and the relationship between the cost of the various operations performed to convert the first sequence into the second sequence. The semantic similarity between the two character strings is then determined and normalized from the minimum semantic distance.

Abstract: A system and method for an integrated, multi-modal, multi-device natural language voice services environment may be provided. In particular, the environment may include a plurality of voice-enabled devices each having intent determination capabilities for processing multi-modal natural language inputs in addition to knowledge of the intent determination capabilities of other devices in the environment. Further, the environment may be arranged in a centralized manner, a distributed peer-to-peer manner, or various combinations thereof. As such, the various devices may cooperate to determine intent of multi-modal natural language inputs, and commands, queries, or other requests may be routed to one or more of the devices best suited to take action in response thereto.

Abstract: An electronic device may operate in different modes of operations. In a first mode of operation, the electronic device may receive user speech via a microphone, generate audio data that represents the user speech, and then send the audio data to one or more remote computing device for analysis. In a second mode of operation, the electronic device may receive user speech via the microphone, generate audio data that represents the user speech, and then analyze the audio data using speech processing. In some instances, the electronic device may operate in the first mode of operation and/or the second mode of operation based on whether the electronic device is receiving power from an external source.

Abstract: Phoneme images are created for keywords and audio files. The keyword images and audio file images are used to identify keywords within the audio file when the phoneme images match. Confidence scores may be determined corresponding to the match. Audio around the keywords may be stored and processed with an automatic speech recognition (ASR) program to verify the keyword match and provide textual and audio context to where the keyword appears within speech.

Abstract: A centralized and robust threat assessment tool is disclosed to perform comprehensive analysis of previously-stored and subsequent communication data, activity data, and other relevant information relating to inmates within a controlled environment facility. As part of the analysis, the system detects certain keywords and key interactions with the dataset in order to identify particular criminal proclivities of the inmate. Based on the identified proclivities, the system assigns threat scores to inmate that represents a relative likelihood that the inmate will carry out or be drawn to certain threats and/or criminal activities. This analysis provides a predictive tool for assessing an inmate's ability to rehabilitate. Based on the analysis, remedial measures can be taken in order to correct an inmate's trajectory within the controlled environment and increase the likelihood of successful rehabilitation, as well as to prevent potential criminal acts.

Abstract: Systems, devices and methods are described herein for segmentation of content, and more specifically for segmentation of content in a content management system. In one aspect, a method may include receiving content associated with speech, text, or closed captioning data. The speech, the text, or the closed captioning data may be analyzed to derive at least one of a topic, subject, or event for at least a portion of the content. The content may be divided into two or more content segments based on the analyzing. At least one of the topic, the subject, or the event may be associated with at least one of the two or more content segments based on the analyzing. At least one of the two or more content segments may then be published such that each of the two or more content segments is individually accessible.

Abstract: Embodiments relate to an intelligent computer platform to decipher and translate an analogical phrase. A phrase is translated, yielding a second language phrase. An idiom database is searched for one or more matching idiom phrases. The idiom phrases are ranked according to similarity to the second language phrase and idiom phrase with a highest similarity ranking is outputted as the final output.

Abstract: A machine translation method is provided, in which a plurality of different first forward-translated sentences is generated resulting from translation of a received translation-source sentence into the second language. It is determined into which of an interrogative form, an affirmative form, a negative form, and an imperative form each of the plurality of different first forward-translated sentences is classified. A plurality of different second forward-translated sentences is determined from the plurality of different first forward-translated sentences, based on the classified form. A plurality of backward-translated sentences is generated resulting from backward translation of the plurality of different second forward-translated sentences into the first language. Upon receiving an operation of the user for selecting one of the plurality of backward-translated sentences, a forward-translated sentence corresponding to the selected backward-translated sentence is output to the information output device.

Abstract: Embodiments relate to an intelligent computer platform to decipher and translate an analogical phrase. A phrase in a source language is parsed into two or more grammatical sub-components, and a category for each parsed grammatical sub-component is identified. Two or more attributes and definitions of the parsed grammatical components are determined in the first language. These attributes and definitions are translated to a second language. A data source is searched for a meaning of the first language phrase, and the first language phrase is translated to a second language phrase. The second language phrase is converged with the attributes and definitions to produce a target phrase. Second language phrases are searched in a second data source and the target phrase is scored against them. A ranking is applied to the second language phrases and a final phrase is output responsive to the ranking.

Abstract: A talking medicine label, bottle, system and method for their manufacture are described. The system and method include use of a recording device by speaking into a microphone and then affixing the talking label to the side of a conventional pill bottle to transform it into a talking pill bottle. The system and method alternatively may include a PC/POS terminal and a speech synthesis device for programming the label with a synthetic-speech recording.

Abstract: A method of performing speech recognition on board an aircraft, a computer program for executing the method, as well as a speech recognition unit for performing speech recognition on board an aircraft. The method comprises receiving a speech signal spoken by a user; performing speaker recognition on the speech signal to identify the user from the speech signal; selecting a speech recognition user profile which is associated with the identified user; and performing speech recognition on the speech signal using the selected user profile.

Abstract: Systems and methods are described for personifying communications. According to at least one embodiment, the computer-implemented method for personifying a natural-language communication includes observing a linguistic pattern of a user. The method may also include analyzing the linguistic pattern of the user and adapting the natural-language communication based at least in part on the analyzed linguistic pattern of the user. In some embodiments, observing the linguistic pattern of the user may include receiving data indicative of the linguistic pattern of the user. The data may be one of verbal data or written data. Written data may include at least one of a text message, email, social media post, or computer-readable note. Verbal data may include at least one of a recorded telephone conversation, voice command, or voice message.

Abstract: This is directed to processing voice inputs received by an electronic device. In particular, this is directed to receiving a voice input and identifying the user providing the voice input. The voice input can be processed using a subset of words from a library used to identify the words or phrases of the voice input. The particular subset can be selected such that voice inputs provided by the user are more likely to include words from the subset. The subset of the library can be selected using any suitable approach, including for example based on the user's interests and words that relate to those interests. For example, the subset can include one or more words related to media items selected by the user for storage on the electronic device, names of the user's contacts, applications or processes used by the user, or any other words relating to the user's interactions with the device.

Abstract: Textual information extraction, parsing, and inferential analysis systems and methods are provided herein. An example method includes extracting content for each of a plurality of types from a corpus of textual information, the plurality of types corresponding to segments of an inference scheme, the inference scheme including a dependency that orders the segments together so as to create a summation of the corpus of textual information when the extracted content is assembled, and assembling one or more inferred statements using the inference scheme and the extracted content.

Abstract: A system can be configured to perform tasks such as converting recorded speech to a sequence of phonemes that represent the speech, converting an input sequence of graphemes into a target sequence of phonemes, translating an input sequence of words in one language into a corresponding sequence of words in another language, or predicting a target sequence of words that follow an input sequence of words in a language (e.g., a language model). In a speech recognizer, the RNN system may be used to convert speech to a target sequence of phonemes in real-time so that a transcription of the speech can be generated and presented to a user, even before the user has completed uttering the entire speech input.