Abstract: Methods, devices, systems, and means for video integration with a home assistant device are described herein. The home assistant device interacts with a person in a video stream by capturing, using a network-enabled outdoor video camera, a video stream of an outdoor location of a premises at which the person is present and analyzing the person appearing in the captured video stream to determine an identity of the person. Based on determining the identity of the person, the home assistant device announces a presence of the person that is outdoors and outputs instructions to the person.

Abstract: Various arrangements are detailed herein related to managing scheduled events using a home assistant and an integrated video service. Using a network-enabled video camera, a video stream of a location may be captured. The video stream captured may be used to determine an identity of a user present at the location. In response to identifying the identity of the user, access to a cloud-based calendar account for the user may be determined to be authorized. The cloud-based calendar account linked with the user may be accessed. A next calendar event mapped to the cloud-based calendar account that is scheduled to occur within a threshold time duration may be determined. A description linked with the next calendar event may be accessed. A network-enabled smart home assistant device may be used to synthesize speech to announce details related to the next event.

Abstract: A method, a computer program product, and a computer system for identifying user preferences and changing settings of a device based on natural language processing. One or more programs running in background on the device capture an input of natural language from a user of the device, match the input of the natural language to a user frustration, map the user frustration to one or more solutions that make one or more changes of settings on the device, apply the one or more changes of settings to set user preference settings on the device, and store the user preference settings in a common store for the user.

Abstract: Non-limiting examples described herein relate to processing for transcoding textual content into audio signals. In some examples, transcoding services are provided over a distributed network, for example, through an interaction between a client device and a server device. For instance, a client device may transmit a selection of a document to a server device. The server device may access a document source for the document and transcode content from the document source into speech. The server device may transmit the transcoded content to the client device, for example, where the client device may output the transcoded content. For instance, the transcoded content may be an audio file that is streamed by the client device.

Abstract: An audio signal processing device comprises a discontinuity detector configured to determine an occurrence of a discontinuity from a sudden increase of an amplitude of decoded audio obtained by decoding the first audio packet which is received correctly after an occurrence of a packet loss, and a discontinuity corrector for correcting the discontinuity of the decoded audio.

Abstract: Approaches to enable a computing device, such as a phone or tablet computer, to determine when a user viewing the content is being distracted or is generally viewing the content with a sufficient level of irregularity, and present an audible representation of the content during the times when the user is deemed distracted. The determination of when the user is distracted or is otherwise viewing the content with irregularity can be performed using sensor data captured by one or more sensors of the computing device. For example, the computing device may analyze the image data captured by one or more cameras, such as by tracking the movement/location of eye pupils of the user and/or tracking the head movement of the user to detect when the user is distracted.

Abstract: An apparatus includes a first calculator configured to determine a long-term noise estimate of the audio signal. The apparatus also includes a second calculator configured to determine a formant-sharpening factor based on the determined long-term noise estimate. The apparatus includes a filter configured to filter a codebook vector to generate a filtered codebook vector. The filter is based on the determined formant-sharpening factor, and the codebook vector is based on information from the audio signal. The apparatus further includes an audio coder configured to generate a formant-sharpened low-band excitation signal based on the filtered codebook vector.

Abstract: Systems, computer-implemented methods, and tangible computer-readable media are provided for voice authentication. The method includes receiving, on a mobile device, a speech sample from a user as part of a request for a restricted-access resource separate from the mobile device. When the user has previously established an identity with the mobile device, the method includes transmitting the speech sample along with the request to an authentication server which compares the speech sample to a previously established speech profile associated with the user and providing access to the restricted-access resource based on a response to the request from the authentication server if the speech sample from the user matches the speech profile on the authentication server with a minimum certainty threshold.

Abstract: Systems, methods, and computer-readable storage media for intelligent caching of concatenative speech units for use in speech synthesis. A system configured to practice the method can identify, in a local cache of text-to-speech units for a text-to-speech voice an absent text-to-speech unit which is not in the local cache. The system can request from a server the absent text-to-speech unit. The system can then synthesize speech using the text-to-speech units and a received text-to-speech unit from the server.

Abstract: Embodiments relate to an audio processing unit that includes a buffer, bitstream payload deformatter, and a decoding subsystem. The buffer stores at least one block of an encoded audio bitstream. The block includes a fill element that begins with an identifier followed by fill data. The fill data includes at least one flag identifying whether enhanced spectral band replication (eSBR) processing is to be performed on audio content of the block. A corresponding method for decoding an encoded audio bitstream is also provided.

Abstract: A method includes identifying, by a computing device including a processor, a plurality of words from data. The method includes determining a location of the computing device. The method includes determining, by the computing device, a sound output level based on the location. The method also includes generating, by the computing device, digital sound data based on the sound output level and the plurality of words identified from the data.

Abstract: A method in a computing device for decoding a weighted finite state transducer (WFST) for automatic speech recognition is described. The method includes sorting a set of one or more WFST arcs based on their arc weight in ascending order. The method further includes iterating through each arc in the sorted set of arcs according to the ascending order until the score of the generated token corresponding to an arc exceeds a score threshold. The method further includes discarding any remaining arcs in the set of arcs that have yet to be considered.

Abstract: A voice controlled assistant has two speakers and stereo component configured to produce high quality stereo sound. The stereo component generates a first channel signal and a second channel signal used to produce stereo sound. The first channel signal is filtered to remove a range of frequencies, such as the low frequency range. The filtered first channel signal is passed to a first transducer associated with a first speaker to output a first part of the stereo sound. The second channel signal, together with the frequency portion removed from the first channel signal, are provided to a second transducer associated with a second speaker to output a second part of the stereo sound. In this manner, the two speaker arrangement plays stereo, without distortion, while preserving all frequencies in the signals.

Abstract: According to an embodiment, a transliteration work support apparatus include an input unit, an extraction unit, a presentation unit, a reception unit, and a correction unit. The input unit receives document information. The extraction unit extracts, as a correction part, a surface expression of the document information that matches a correction pattern expressing a plurality of surface expressions having the same regularity in way of correction in one form. The presentation unit presents a way of correction defined in accordance with the correction pattern used in the extraction of the correction part. The reception unit receives selection of the way of correction. The correction unit corrects the correction part based on the selected way of correction.

Abstract: An audio signal decoding method includes: obtaining mode information of a high frequency band signal of an audio signal and indices of a low frequency band signal of the audio signal by parsing a received bitstream; obtaining the low frequency band signal based on the indices; predicting an excitation signal of a high frequency band signal based on the low frequency band signal; and reconstructing the high frequency band signal based on the frequency envelope and the excitation signal. A manner for obtaining the frequency envelope of the high frequency band signal when mode information indicates the high frequency band signal is a harmonic type signal is different from a manner for obtaining the frequency envelope of the high frequency band signal when the mode information indicates the high frequency band signal is not a harmonic type signal.

Abstract: Systems and methods to process and/or present information relating to voice messages for a user that are received from other persons. In one embodiment, a method includes: receiving first data associated with prior communications for the user on a mobile device; receiving a voice message for the user; transcribing the voice message using the first data to provide a transcribed message; and sending the transcribed message to the mobile device for display to the user. In one embodiment, links associated with person profiles are also provided for the user.

Abstract: A speech coding method of reducing error propagation due to voice packet loss, is achieved by limiting or reducing a pitch gain only for the first subframe or the first two subframes within a speech frame, the excitation of a next frame is obtained according to the reduced or limited pitch gain value of the first subframe, and the next frame is encoded according to the obtained excitation. The method is used for a voiced speech class.

Abstract: Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.

Abstract: Various embodiments are included for adjusting a search result user interface when a foreign language search query is detected. A search query associated with a search request is obtained. A language of the search query is identified. Search results are obtained from a site corresponding to the language. Additionally, a translation of the search query is obtained if allowed for a corresponding product category.

Abstract: An apparatus comprising a natural language processor, a mapper, a string comparator, a nutrient calculator, and a diet planning module, the diet planning module configured to generate a diet action control, the diet action control comprising instructions to operate the client device to perform a diet change recommendation on the client device, and apply the diet action control to the client device.