Abstract: A method of operating a customer utterance analysis system includes obtaining a subset of utterances from among a first set of utterances. The method includes encoding, by a sentence encoder, the subset of utterances into multi-dimensional vectors. The method includes generating reduced-dimensionality vectors by reducing a dimensionality of the multi-dimensional vectors. Each vector of the reduced-dimensionality vectors corresponds to an utterance from among the subset of utterances. The method includes performing clustering on the reduced-dimensionality vectors. The method includes, based on the clustering performed on the reduced-dimensionality vectors, arranging the subset of utterances into clusters. The method includes obtaining labels for a least two clusters from among the clusters. The method includes generating training data based on the obtained labels. The method includes training a neural network model to predict an intent of an utterance based on the training data.

Abstract: Provided is to prevent a false determination due to an attachment condition of an apparatus that transmits and receives an acoustic signal, and perform accurate personal authentication. A personal authentication device includes: a personal authentication means that authenticates an individual by using first information at least including an acoustic characteristic calculated from an acoustic signal propagating through the head of the user, which is detected by an apparatus being attached on a head of a user for transmitting and receiving the acoustic signal, and a feature amount extracted from the acoustic characteristic; an attachment trouble rule storage means that stores an attachment trouble rule for detecting an attachment trouble with the apparatus; and an attachment trouble detection means that detects a trouble with an attachment state of the apparatus when the first information satisfies the attachment trouble rule.

Abstract: Provided is to prevent a false determination due to an attachment condition of an apparatus that transmits and receives an acoustic signal, and perform accurate personal authentication. A personal authentication device includes: a personal authentication means that authenticates an individual by using first information at least including an acoustic characteristic calculated from an acoustic signal propagating through the head of the user, which is detected by an apparatus being attached on a head of a user for transmitting and receiving the acoustic signal, and a feature amount extracted from the acoustic characteristic; an attachment trouble rule storage means that stores an attachment trouble rule for detecting an attachment trouble with the apparatus; and an attachment trouble detection means that detects a trouble with an attachment state of the apparatus when the first information satisfies the attachment trouble rule.

Abstract: Provided is to prevent a false determination due to an attachment condition of an apparatus that transmits and receives an acoustic signal, and perform accurate personal authentication. A personal authentication device includes: a personal authentication means that authenticates an individual by using first information at least including an acoustic characteristic calculated from an acoustic signal propagating through the head of the user, which is detected by an apparatus being attached on a head of a user for transmitting and receiving the acoustic signal, and a feature amount extracted from the acoustic characteristic; an attachment trouble rule storage means that stores an attachment trouble rule for detecting an attachment trouble with the apparatus; and an attachment trouble detection means that detects a trouble with an attachment state of the apparatus when the first information satisfies the attachment trouble rule.

Abstract: A method, decoder, and program code for controlling a concealment method for a lost audio frame is provided. A first audio frame and a second audio frame of the received audio signal are decoded to obtain modified discrete cosine transform (MDCT) coefficients. Values of a first spectral shape based upon the MDCT coefficients decoded from the first audio frame decoded and values of a second spectral shape based upon MDCT coefficients decoded from the second audio frame decoded are determined, the spectral shapes each comprising a number of sub-bands. The values of the spectral shapes and frame energies of the first audio frame and second audio frame are transformed into representations of FFT based spectral analyses. A transient condition is detected based on the representations of the FFTs. Responsive to detecting the transient condition, the concealment method is modified by selectively adjusting a spectrum magnitude of a substitution frame spectrum.

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

Abstract: Described herein is a method for generating a modified bitstream on a source device, wherein the method includes the steps of: a) receiving, by a receiver, a bitstream including coded media data; b) generating, by an embedder, payload of additional media data and embedding the payload in the bitstream for obtaining, as an output from the embedder, a modified bitstream including the coded media data and the payload of the additional media data; and d) outputting the modified bitstream to a sink device. Described is further a method for processing said modified bitstream on a sink device. Described are moreover a respective source device and sink device as well as a system of a source device and a sink device and respective computer program products.

Abstract: An improved concept for coding sample values of a spectral envelope is obtained by combining spectrotemporal prediction on the one hand and context-based entropy coding the residuals, on the other hand, while particularly determining the context for a current sample value dependent on a measure of a deviation between a pair of already coded/decoded sample values of the spectral envelope in a spectrotemporal neighborhood of the current sample value. The combination of the spectrotemporal prediction on the one hand and the context-based entropy coding of the prediction residuals with selecting the context depending on the deviation measure on the other hand harmonizes with the nature of spectral envelopes.

Abstract: Systems and methods are provided to implement and facilitate cross-fading, interstitials and other effects/processing of two or more media elements in a personalized media delivery service to experience consistent high quality. The effects or crossfade processing may occur on the broadcast/publisher/server-side, but may be personalized to a specific user, allowing a personalized experience for each user, where the processing burden is minimized on the downstream side/client device. This approach enables a consistent user experience, independent of client device capabilities. A large-scale personalized content delivery service may be implemented by limiting the processing to the first and last chunks of any file. In exemplary embodiments, this type of processing may easily be accommodated in cloud computing technology, where first and last files are extracted and processed within the cloud to meet the required load.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: examining social network data of a user, wherein the social network data specifies social network connections of the user; obtaining from the user voice data defining a vocal utterance request of the user; converting the voice data defining the vocal utterance request of the user into a text based message; subjecting the text based message to natural language processing; determining a response message to the vocal utterance request of the user, wherein the determining the response data to the vocal utterance request of the user is performed in dependence on the examining of the social network data of the user; and presenting the response message to the user.

Abstract: The present document relates to audio source coding systems which make use of a harmonic transposition method for high frequency reconstruction (HFR), as well as to digital effect processors, e.g. exciters, where generation of harmonic distortion add brightness to the processed signal, and to time stretchers where a signal duration is prolonged with maintained spectral content. A system and method configured to generate a time stretched and/or frequency transposed signal from an input signal is described. The system comprises an analysis filterbank configured to provide an analysis subband signal from the input signal; wherein the analysis subband signal comprises a plurality of complex valued analysis samples, each having a phase and a magnitude. Furthermore, the system comprises a subband processing unit configured to determine a synthesis subband signal from the analysis subband signal using a subband transposition factor Q and a subband stretch factor S.

Abstract: In general, techniques are described for quantizing spatial components based on bit allocations determined for psychoacoustic audio coding. A device comprising a memory and one or more processors may perform the techniques. The memory may store a bitstream including an encoded foreground audio signal and a corresponding quantized spatial component. The one or more processors may perform psychoacoustic audio decoding with respect to the encoded foreground audio signal to obtain a foreground audio signal, and determine, when performing the psychoacoustic audio decoding, a first bit allocation for the encoded foreground audio signal. The one or more processors may also determine, based on the first bit allocation, a second bit allocation, and dequantize, based on the second bit allocation, the quantized spatial component to obtain a spatial component. The one or more processors may reconstruct, based on the foreground audio signal and the spatial component, scene-based audio data.

Abstract: An apparatus for generating a decoded two-channel signal, comprising: a parametric decoder for providing parametric data for a second set of second spectral portions and a two-channel identification identifying for a second spectral portion of the second set of second spectral portions either a first two-channel representation for the second spectral portion of the second set of second spectral portions or a second two-channel representation for the second spectral portion of the second set of second spectral portions, the second two-channel representation being different from the first two-channel representation; and a frequency regenerator for regenerating the second spectral portion of the second set of second spectral portions depending on a first spectral portion of a first set of first spectral portions, the parametric data for the second spectral portion of the second set of second spectral portions and the two-channel identification for the second spectral portion of the second set of second spectral

Abstract: A method, computer system, and a computer program product for generating a conversational bot for an application programming interface (API) is provided. The present invention may include parsing an API schema. The present invention may include generating sentences for the conversational bot from the parsed API schema. The present invention may include constructing the conversational bot by training a deep learning model. The present invention may include receiving a natural language expression from a user. The present invention may include determining whether the natural language expression is enough to activate the bot.

Abstract: An apparatus for encoding directional audio coding parameters including diffuseness parameters and direction parameters includes: a parameter calculator for calculating the diffuseness parameters with a first time or frequency resolution and for calculating the direction parameters with a second time or frequency resolution; and a quantizer and encoder processor for generating a quantized and encoded representation of the diffuseness parameters and the direction parameters.

Abstract: Systems and methods for item recommendation are described. One or more embodiments of the systems and methods include generating a hidden vector representation for each word of a source document; removing at least one word from the source document based on the hidden vector representation using a summarization network to obtain a summary document; filtering a plurality of candidate documents based on the source document to obtain a plurality of filtered candidate documents; comparing the summary document to each of the filtered candidate documents to obtain a ranking score for each of the filtered candidate documents; and identifying a relevant candidate document from the filtered candidate documents based on the ranking score.

Abstract: An apparatus for encoding directional audio coding parameters comprising diffuseness parameters and direction parameters having a parameter calculator (100) for calculating the diffuseness parameters with a first time or frequency resolution and for calculating the direction parameters with a second time or frequency resolution; and a quantizer and encoder processor (200) for generating a quantized and encoded representation of the diffuseness parameters and the direction parameters.

Abstract: A speech signal processing method and apparatus. The method includes preprocessing a speech signal that is in a first frequency band and that is collected by an ear canal speech collector, to obtain a first speech signal; preprocessing a speech signal that is in a second frequency band and that is collected by at least one external speech collector, to obtain an external speech signal, where frequency ranges of the first frequency band and the second frequency band are different; performing correlation processing on the first speech signal and the external speech signal to obtain a second speech signal; and outputting a target speech signal, where the target speech signal includes the first speech signal and the second speech signal.

Abstract: Systems are provided for multilingual speech data processing. A language identification module is configured to analyze spoken utterances in an audio stream and to detect at least one language corresponding to the spoken language utterances. The language identification module detects that a first language corresponds to the first portion of the audio stream. A first transcription of the first portion of the audio stream in the first language is generated and stored in a cache. A second transcription of a second portion of the audio stream in the first language is also generated and stored. When the second portion of the audio stream corresponds to a second language, a third transcription is generated in the second language using a second speech recognition engine configured to transcribe spoken language utterances in the second language. Then, the second transcription is replaced with the third transcription in the cache and any displayed instances.

Abstract: A method for using a neural network model for natural language processing (NLP) includes receiving training data associated with a source domain and a target domain; and generating one or more query batches. Each query batch includes one or more source tasks associated with the source domain and one or more target tasks associated with the target domain. For each query batch, class representations are generated for each class in the source domain and the target domain. A query batch loss for the query batch is generated based on the corresponding class representations. An optimization is performed on the neural network model by adjusting its network parameters based on the query batch loss. The optimized neural network model is used to perform one or more new NLP tasks.