Abstract: The technology described in this document can be embodied in a computer-implemented method that includes presenting a first user-interface that includes a user-selectable menu of multiple virtual personal assistant (VPA) service providers, and receiving a user-selection identifying a particular VPA service provider. The method also includes receiving a first signal representing input speech data, and processing the first signal to generate a first electronic file that includes at least a portion of the input speech data, the first electronic file being generated in accordance with a specification of the particular VPA service provider. The method further includes transmitting the first electronic file to one or more remote computing devices associated with the particular VPA service provider, receiving at least a second electronic file including a response to the input speech data, and causing an acoustic transducer to generate an acoustic output based on the second electronic file.

Abstract: A system and method for performing text-to-speech (TTS) processing of textual works, such a literary works. The system and method process text of these works and determine offsets corresponding to one or more of chapters, paragraphs, sentences, words, section of dialogs, sections of other context. Using these offsets, the system and method determine which portion and how much of a work to process using TTS processing at a time to produce a high quality audio output. This audio output may then be sent to a user device to allow the user device to play the audio output of the TTS processing.

Abstract: A computer-readable speaker-adapted speech engine acoustic model can be generated. The generating of the acoustic model can include performing speaker-specific adaptation of one or more layers of the model to produce one or more adaptive layers comprising layer weights, with the speaker-specific adaptation comprising a data size reduction technique. The data size reduction technique can be threshold value adaptation, corner area adaptation, diagonal-based quantization, adaptive matrix reduction, or a combination of these reduction techniques. The speaker-adapted speech engine model can be accessed and used in performing speech recognition on computer-readable audio speech input via a computerized speech recognition engine.

Abstract: Systems and methods for modifying a computer-based speech recognition system. A speech utterance is processed with the computer-based speech recognition system using a set of internal representations, which may comprise parameters for recognizing speech in a speech utterance, such as parameters of an acoustic model and/or a language model. The computer-based speech recognition system may perform a first task in response to the processed speech utterance. The utterance may also be provided to a human who performs a second task based on the utterance. Data indicative of the first task, performed by the computer system, is compared to data indicative of a second task, performed by the human in response to the speech utterance. Based on the comparison, the set of internal representations may be updated or modified to improve the speech recognition performance and capabilities of the speech recognition system.

Abstract: Techniques are described related to improved intercom-style communication using a plurality of computing devices distributed about an environment. In various implementations, voice input may be received, e.g., at a microphone of a first computing device of multiple computing devices, from a first user. The voice input may be analyzed and, based on the analyzing, it may be determined that the first user intends to convey a message to a second user. A location of the second user relative to the multiple computing devices may be determined, so that, based on the location of the second user, a second computing device may be selected from the multiple computing devices that is capable of providing audio or visual output that is perceptible to the second user. The second computing device may then be operated to provide audio or visual output that conveys the message to the second user.

Abstract: Participants of a phone conference can share electronic data without a need to exchange passwords to link two devices nor to login to access data. The invention is resistant to eavesdropping, and provides methods, devices and systems to easily and automatically find, identify and authenticate participants on a computer network for electronic data exchange. Samples of the audio are used to create a stream of audio fingerprints which are sent to a matching service. This matching service finds the fingerprints that correspond to the same conversation, and exchanges identifiers. When instructed by the user, the device can setup a secure data connection.

Abstract: A dynamic text-to-speech (TTS) process and system are described. In response to receiving a command to provide information to a user, a device retrieves information and determines user and environment attributes including: (i) a distance between the device and the user when the user uttered the query; and (ii) voice features of the user. Based on the user and environment attributes, the device determines a likely mood of the user, and a likely environment in which the user and user device are located in. An audio output template matching the likely mood and voice features of the user is selected. The audio output template is also compatible with the environment in which the user and device are located. The retrieved information is converted into an audio signal using the selected audio output template and output by the device.

Abstract: Systems and methods for authorizing a user of a portable communications device entail sampling a user utterance via both an air mic (audio mic) and a conduction mic (surface mic or bone conduction mic). The difference between these signals is unique to each user since the tissues of each user will differ with respect to audio conduction. This difference may be characterized via a transform including magnitude, phase and time delay components. If the transform for a prospective user matches a stored transform for an authorized user, then the prospective user may be granted access.

Abstract: A method, device, and a non-transitory computer-readable storage medium are provided for identifying information in an electronic message. The information from the electronic message may be identified according to a template that has been trained to classify the information included in the electronic message.

Abstract: A method for trait prediction includes receiving a text sequence and generating character embeddings for characters of the text sequence. Word representations for words of the text sequence are generated with a trained character sequence model, based on the character embeddings. A sequence representation is generated for the text sequence with a trained word sequence model, based on the word representations. At least one trait prediction is generated with a trained trait model, based on the sequence representation.

Abstract: A method and a system for generating a target character sequence from a semantic representation including a sequence of characters are provided. The method includes adapting a target background model, built from a vocabulary of words, to form an adapted background model. The adapted background model accepts subsequences of an input semantic representation as well as words from the vocabulary. The input semantic representation is represented as a sequence of character embeddings, which are input to an encoder. The encoder encodes each of the character embeddings to generate a respective character representation. A decoder then generates a target sequence of characters, based on the set of character representations. At a plurality of time steps, a next character in the target sequence is selected as a function of a previously generated character(s) of the target sequence and the adapted background model.

Abstract: One embodiment of the present invention provides a system for providing context-based web services to a user. During operation, the system may receive a sentence as input from a user. The system may determine a sentence structure of the sentence, and determine whether there is an entry in a database corresponding to the sentence structure. Responsive to determining that there is no entry in the database corresponding to the sentence structure, the system may engage in a dialog with the user. The system may extract one or more parameters of the sentence based on information from the dialog. The system may obtain contextual and background information associated with the parameters. The system may then determine a set of arguments based on the parameters and the contextual and background information, and interact with web services to perform an action and provide a response to the user.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A loudness of an input voice signal is detected to obtain a reference loudness. Reference loudness gains corresponding to frequency bands are calculated according to the reference loudness and wide dynamic range compression curves corresponding to the frequency bands. Loudnesses of filter signals of the frequency bands are adjusted according to the reference loudness gains of the frequency bands.

Abstract: Methods and arrangements for effecting a cloud representation of audio content. An audio cloud is created and rendered, and user interaction with at least a clip portion of the audio cloud is afforded.

Abstract: A method for generating a test-speaker-specific adaptive system for recognising sounds in speech spoken by a test speaker; the method employing: (i) training data comprising speech items spoken by the test speaker; and (ii) an input network component and a speaker adaptive output network, the input network component and speaker adaptive output network having been trained using training data from training speakers; the method comprising: (a) using the training data to train a test-speaker-specific adaptive model component of an adaptive model comprising the input network component, and the test-speaker-specific adaptive model component, and (b) providing the test-speaker-specific adaptive system comprising the input network component, the trained test-speaker-specific adaptive model component, and the speaker-adaptive output network.

Abstract: Disclosed are various embodiments for an automated service agent. Natural language inputs are obtained from a client. The natural language inputs and other data are input to machine learning models to identify intents reflected in the natural language inputs. A state in a workflow is updated to reflect the identified intents. Responses may be communicated to the client to further progress in the workflow.

Abstract: Methods, systems, and apparatus for receiving data identifying an application and a voice command trigger term, validating the received data, inducting the received data to generate an intent that specifies the application, the voice command trigger term, and one or more other voice command trigger terms that are determined based at least on the voice command trigger term, and storing the intent at a contextual intent database, wherein the contextual intent database comprises one or more other intents.

Abstract: A voice controlled medical system with improved speech recognition includes a first microphone array, a second microphone array, a controller in communication with the first and second microphone arrays, and a medical device operable by the controller. The controller includes a beam module that generates a first beamed signal using signals from the first microphone array and a second beamed signal using signals from the second microphone array. The controller also includes a comparison module that compares the first and second beamed signals and determines a correlation between the first and second beamed signals. The controller also includes a voice interpreting module that identifies commands within the first and second beamed signals if the correlation is above a correlation threshold. The controller also includes an instrument control module that executes the commands to operate said medical device.

Abstract: Systems, methods and apparatus are disclosed for linking virtual content to various types of object, such a static physical objects, through the use of triggers of varying formats. The virtual content can be updated by a content curator over time. The virtual content can be translated into a plurality of languages and can be selectively transmitted to a mobile communications device upon receipt of the trigger.

Abstract: Methods and arrangements for effecting a cloud representation of audio content. An audio cloud is created and rendered, and user interaction with at least a clip portion of the audio cloud is afforded.