Abstract: A method for spectrum recovery in spectral decoding of an audio signal, comprises obtaining of an initial set of spectral coefficients representing the audio signal, and determining a transition frequency. The transition frequency is adapted to a spectral content of the audio signal. Spectral holes in the initial set of spectral coefficients below the transition frequency are noise filled and the initial set of spectral coefficients are bandwidth extended above the transition frequency. Decoders and encoders being arranged for performing part of or the entire method are also illustrated.

Abstract: A received signal represents a user's speech. A first speaker recognition process is performed on a first portion of the received signal, to obtain a first output result. A second speaker recognition process is performed on a second portion of the received signal that is different from the first portion of the received signal, to obtain a second output result. The second speaker recognition process is different from the first speaker recognition process. The first and second output results are combined to obtain a combined output result indicating a likelihood that the user is a registered user.

Abstract: A system and method is provided for providing searchable customer call indexes. Consistent with disclosed embodiments, a system may receive call information associated with telephone conversations between callers and a vendor, the call information including an audio recording or transcript for each telephone conversation. The system may also identify one or more keywords from the audio recordings or transcripts and index the call information into one or more indexes based on the identified keywords. Finally, the system may determine search results responsive to a search query based on the indexing. In some embodiments, changes to customer service may be identified based on the search results.

Abstract: A dialog method carried out by a dialog system includes an agent that performs a dialog with a user. The dialog method carried out by the dialog system includes a speech receiving step in which the dialog system receives input of a user speech which is a speech of the user, a first presentation step in which when the dialog system cannot obtain any recognition result of a desired level corresponding to the user speech, the dialog system presents a speech which does not include any content words as a first agent speech which is a speech of the agent uttered immediately after the user speech and a second speech step in which the dialog system presents a speech generated or selected not based on the user speech as a second agent speech which is a speech of an agent uttered after uttering the first agent speech.

Abstract: A translation device includes an input unit configured to receive an input sentence in an original language, a controller configured to generate a first translation sentence obtained by translation of the input sentence into a first language, and a display. The controller generates a second translation sentence obtained by translation of the input sentence into a second language different from the first language, a first reverse translation sentence obtained by reverse translation of the first translation sentence into the original language, and a second reverse translation sentence obtained by reverse translation of the second translation sentence into the original language.

Abstract: A morpheme analysis unit sets beforehand a meaning-candidate tag and a sentimental theme tag for a morpheme required to be input as a text. A syntax analysis unit generates an index where a clause including a meaning-candidate tag and a sentimental theme tag and a type of each tag. A meaning attribute extraction unit recognizes a clause including a meaning-candidate and a type of tag with reference to the index, and then applies a meaning attribute rule, sets a meaning attribute tag for a necessary clause, and updates the index. A sentimental analysis unit also recognizes a clause including a sentimental theme tag and a clause including a meaning attribute tag with reference to the index, and then applies a sentimental analysis rule and sets a sentimental attribute tag for a necessary clause.

Abstract: An interactive speech recognition system is provided for interactively interpreting a spoken phrase. The speech recognition system includes a phrase interpretation module which attempts to accurately interpret a spoken phrase by interpreting each individual term of the spoken phrase. A term interpretation module attempts to accurately interpret each individual term of the spoken phrase not accurately interpreted by the phrase interpretation module, by using a spoken spelling of the term provided by a user. An interactive spelling module attempts to interactively spell at least a portion of an individual term of the spoken phrase not accurately interpreted by the term interpretation module, by enabling a user to interactively select at least one individual character of the term of the spoken phrase from a plurality of characters.

Abstract: The technology disclosed relates to computer-implemented conversational agents and particularly to detecting a point in the dialog (end of turn, or end of utterance) at which the agent can start responding to the user. The technology disclosed provides a method of incrementally parsing an input utterance with multiple parses operating in parallel. The technology disclosed includes detecting an interjection point in the input utterance when a pause exceeds a high threshold, or detecting an interjection point in the input utterance when a pause exceeds a low threshold and at least one of the parallel parses is determined to be interruptible by matching a complete sentence according to the grammar. The conversational agents start responding to the user at a detected interjection point.

Abstract: Smart speaker mechanisms are provided for processing audio sample data captured by the audio capture device is provided. The mechanisms capture one or more audio samples from a monitored environment and store the captured one or more audio samples in the audio sample buffer. The one or more captured audio samples are analyzed to determine whether the one or more captured audio samples represent a potential wake sound for initiating a responsive action by the smart speaker device. The potential wake sound is a variable sound determined to not be a normal ambient sound of the monitored environment. In response to determining that the one or more captured audio samples represent a potential wake sound for initiating a responsive action by the smart speaker device, the mechanisms initiate performance of the responsive action by the smart speaker device.

Abstract: An electronic device and a method for predicting a response are provided. The electronic device includes a display and a processor configured to receive at least one message, identify at least one contextual category of the at least one message, predict at least one response for the at least one message from a language model based on the at least one contextual category, and control the display to display the at least one predicted response.

Abstract: A numerical sound synthesis method for representing data as audio for use in data sonification employing a Hilbert Space eigenfunction model of human auditory perception is described. The synthesis method comprises approximating an eigenfunction equation representing a model of human hearing, calculating the approximation to each of a plurality of eigenfunctions from at least one aspect of the eigenfunction equation, and storing the approximation to each of a plurality of eigenfunctions. The approximation to each of a plurality of eigenfunctions represents a perception-oriented basis functions for mathematically representing audio information in a Hilbert-space representation of an audio signal space. The model of human hearing can include a bandpass operation with a bandwidth having the frequency range of human hearing and a time-limiting operation approximating the time duration correlation window of human hearing.

Abstract: Example aspects of the present disclosure are directed to systems and methods that employ a machine-learned opinion classification model to classify portions (e.g., sentences, phrases, paragraphs, etc.) of documents (e.g., news articles, web pages, etc.) as being opinions or not opinions. Further, in some implementations, portions classified as opinions can be considered for inclusion in an informational display. For example, document portions can be ranked according to importance and selected for inclusion in an informational display based on their ranking. Additionally or alternatively, for systems which access and consider multiple documents, the portions of a document that are classified as opinion can be compared to similarly-classified portions of other documents to perform document clustering, to ensure diversity within a presentation, and/or other tasks.

Abstract: A facility for representing a mandate occurring in an authority document with a control is described. For each of one or more controls in a set of existing controls, the facility determines a similarity score measuring the similarity of the mandate and the control; where the similarity score exceeds a similarity threshold, the facility links the mandate to the control. Where the mandate is not linked to any control in the set of controls, the facility adds a control to the set of controls that is based on the mandate, and links the mandate to the added control.

Abstract: A data collection system is based on a general set of dialogue acts which are derived from a database schema. Crowd workers perform two types of tasks: (i) identification of sensical dialogue paths and (ii) performing context-dependent paraphrasing of these dialogue paths into real dialogues. The end output of the system is a set of training examples of real dialogues which have been annotated with their logical forms. This data can be used to train all three components of the dialogue system: (i) the semantic parser for understanding context-dependent utterances, (ii) the dialogue policy for generating new dialogue acts given the current state, and (iii) the generation system for both deciding what to say and how to render it in natural language.

Abstract: Implementations of the present specification disclose methods, apparatuses, and devices for generating word vectors. The method includes: obtaining individual words by segmenting a corpus; establishing a feature vector of each word based on n-ary characters; training a recurrent neural network based on the feature vectors of the obtained words and feature vectors of context words associated with the obtained words in the corpus; and generating a word vector for each obtained word based on the feature vector of the obtained word and the trained recurrent neural network.

Abstract: A system and method for providing aural guidance in imaging a document is disclosed. Visually impaired people may have difficulty when imaging a document with a mobile computing device. The system and method may analyze the image of the document in the imaging device, and output one or more aural directions in order for the user to move the document and/or camera for proper imaging of the document. In that regard, those with visual impairments may be assisted in imaging documents using a mobile computing device.

Abstract: A parser for natural language text is provided. The parser is trained by accessing a corpus of labeled utterances. The parser extracts details of the syntactic tree structures and part of speech tags from the labeled utterances. The details extracted from the tree structures include Simple Links which are the key to the improved efficiency of this new approach. The parser creates a language model using the details that were extracted from the corpus. The parser then uses the language model to parse utterances.

Abstract: Building safety systems, methods, and mediums are provided. A method includes receiving a voice input by the building safety system. The method includes receiving voice data produced by a speech recognition process performed on the voice input. The method includes determining a response to the voice input based on the voice data. The method includes producing the response by the building safety system.

Abstract: An audio processor for processing an audio signal includes a target phase measure determiner for determining a target phase measure for the audio signal in a time frame, a phase error calculator for calculating a phase error using a phase of the audio signal in the time frame and the target phase measure, and a phase corrector configured for correcting the phase of the audio signal in the time frame using the phase error.

Abstract: In some implementations, (i) audio data representing a voice command spoken by a speaker and (ii) a speaker identification result indicating that the voice command was spoken by the speaker are obtained. A voice action is selected based at least on a transcription of the audio data. A service provider corresponding to the selected voice action is selected from among a plurality of different service providers. One or more input data types that the selected service provider uses to perform authentication for the selected voice action are identified. A request to perform the selected voice action and (i) one or more values that correspond to the identified one or more input data types are provided to the service provider.