Abstract: A speech translation system and methods for cross-lingual communication that enable users to improve and customize content and usage of the system and easily. The methods include, in response to receiving an utterance including a first term associated with a field, translating the utterance into a second language. In response to receiving an indication to add the first term associated with the field to a first recognition lexicon, adding the first term associated with the field and the determined translation to a first machine translation module and to a shared database for a community associated with the field of the first term associated with the field, wherein the first term associated with the field added to the shared database is accessible by the community.

Abstract: Embodiments relate to decoding communications with token sky maps. At least one electronic communication including emoticons having a non-original meaning is received. A candidate meaning is determined for the emoticons having the non-original meaning in the at least one electronic communication based at least in part on token neighborhood distribution structures. The candidate meaning for the emoticons having the non-original meaning is caused to be displayed on at least one device.

Abstract: Embodiments of the present disclosure include systems and methods for determining position values for training data that is used to train transformer models. In some embodiments, a set of input data for training a transformer model is received. The set of input data comprises a set of tokens. Based on an offset value, a set of successive position values for the set of tokens is determined. Each position value in the set of successive position values represents a position of a token in the set of tokens relative to other tokens in the set of tokens. A set of training data is generated to comprise the set of tokens and the set of successive position values. The transformer model is trained using the set of training data.

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: An electronic device configures a device-agnostic voice assistant library for execution on the electronic device based on the electronic device having a first device type. The electronic device also selects an implementation for the voice assistant library. After the configuring, the electronic device receives a verbal input from a user. It extracts request information from the verbal input by processing the verbal input using the voice assistant library executing on the device. It transmits a request to a remote system, the request including the extracted request information. The electronic device receives a response to the request. The response is generated by the remote system in accordance with the extracted request information. The electronic device performs an operation in accordance with the response by one or more voice processing modules of the configured voice assistant library.

Abstract: Disclosed speech recognition techniques improve user-perceived latency while maintaining accuracy by: receiving an audio stream, in parallel, by a primary (e.g., accurate) speech recognition engine (SRE) and a secondary (e.g., fast) SRE; generating, with the primary SRE, a primary result; generating, with the secondary SRE, a secondary result; appending the secondary result to a word list; and merging the primary result into the secondary result in the word list. Combining output from the primary and secondary SREs into a single decoder as described herein improves user-perceived latency while maintaining or improving accuracy, among other advantages.

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: An electronic device stores a voice assistant library for execution on the electronic device based on the electronic device having a first device type. The electronic device receives a verbal input from a user. It extracts request information from the verbal input by processing the verbal input using the voice assistant library executing on the device. It transmits a request to a remote system. The electronic device receives a response to the request. The response is generated by the remote system. The electronic device performs an operation in accordance with the response by one or more voice-processing modules of the configured voice assistant library.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: obtaining, for each frame in a stream of frames from a video in which faces of one or more speakers have been detected, a respective per-frame face embedding of the face of each speaker; processing, for each speaker, the per-frame face embeddings of the face of the speaker to generate visual features for the face of the speaker; obtaining a spectrogram of an audio soundtrack for the video; processing the spectrogram to generate an audio embedding for the audio soundtrack; combining the visual features for the one or more speakers and the audio embedding for the audio soundtrack to generate an audio-visual embedding for the video; determining a respective spectrogram mask for each of the one or more speakers; and determining a respective isolated speech spectrogram for each speaker.

Abstract: Techniques are disclosed to optimize feature selection in generating betas for a feature dictionary of a neuro-linguistic Cognitive AI System. A machine learning engine receives a sample vector of input data to be analyzed by the neuro-linguistic Cognitive AI System. The neuro-linguistic Cognitive AI System is configured to generate multiple betas for each of a plurality of sensors. The machine learning engine identifies a sensor specified in the sample vector and selects optimization parameters for generating betas based on the identified sensor.

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: Aspects include methods, systems, and computer-program products providing virtual assistant domain functionality. A natural language query including one or more words is received. A collection of natural language modules is accessed. The collection natural language modules are configured to process sets of natural language queries. A natural language module, from the collection of natural language modules, is identified to interpret the natural language query. An interpretation of the natural language query is computed using the identified natural language module. A response to the natural language query is returned using the computed interpretation.

Abstract: A system for removing noise from an audio signal is described. For example, noise caused by content playing in the background during a voice command or phone call may be removed from the audio signal representing the voice command or phone call. By removing noise, the signal to noise ratio of the audio signal may be improved.

Abstract: An encoder operable to filter audio signals into a plurality of frequency band components, generate quantized digital components for each band, identify a potential for pre-echo events within the generated quantized digital components, generate an approximate signal by decoding the quantized digital components using inverse pulse code modulation, generate an error signal by comparing the approximate signal with the sampled audio signal, and process the error signal and quantized digital components. The encoder operable to process the error signal by processing delayed audio signals and Q band values, determining the potential for pre-echo events from the Q band values, and determining scale factors and MDCT block sizes for the potential for pre-echo events.

Abstract: In exemplary embodiments of the present invention 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 so that each client or user has a consistent high quality experience. The effects or crossfade processing can occur on the broadcast, publisher or server-side, but can still be personalized to a specific user, thus still allowing a personalized experience for each individual user, in a manner where the processing burden is minimized on the downstream side or client device. This approach enables a consistent user experience, independent of client device capabilities, both static and dynamic.

Abstract: A method includes, during a teleconference between a first audio input/output device and a second audio input/output device, receiving, at an analysis and response device, a signal indicating a spoken command, the spoken command associated with a command mode. The method further includes, in response to receiving the signal, generating, at the device, a reply message based on the spoken command, the reply message to be output to one or more devices selected based on the command mode. The one or more devices includes the first audio input/output device, the second audio input/output device, or a combination thereof.

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: 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: Techniques are described for providing information during a service session, using an intelligent agent. The intelligent agent executes as a process to monitor communications exchanged during a service session between an individual and a service representative (SR) within a service environment. The agent analyzes the communications to identify questions or other topics that are posed by the individual during the service session. The agent retrieves stored data related to such questions or other topics, and generates a message to address each question or other topic. The message is injected into the service session to be presented to the individual, to supplement the conversation that is taking place between the SR and the individual. In some implementations, the agent monitors the communications, generates the message, and/or injects the message into the service session at least partly autonomously of any explicit action taken by the SR.

Abstract: A method comprises receiving a new data set; identifying at least one prior data set of a plurality of prior data sets that matches the new data set; generating a natural language data science problem statement for the new data set based on information associated with the at least prior one data set that matches the new data set; outputting the generated natural language data science problem statement for user verification; and in response to receiving user input verifying the natural language generated data science problem statement, generating one or more AutoAI configuration settings for the new data set based on one or more AutoAI configuration settings associated with the at least one prior data set that matches the new data set.