Abstract: A direct speech-to-speech translation (S2ST) model includes an encoder configured to receive an input speech representation that to an utterance spoken by a source speaker in a first language and encode the input speech representation into a hidden feature representation. The S2ST model also includes an attention module configured to generate a context vector that attends to the hidden representation encoded by the encoder. The S2ST model also includes a decoder configured to receive the context vector generated by the attention module and predict a phoneme representation that corresponds to a translation of the utterance in a second different language. The S2ST model also includes a synthesizer configured to receive the context vector and the phoneme representation and generate a translated synthesized speech representation that corresponds to a translation of the utterance spoken in the different second language.

Abstract: A non-transitory computer readable storage medium has instructions executed by a processor to invoke an image processing module to ingest a digital invoice. An evaluation module derives metrics from the digital invoice. A semantic document processing module forms entity extracts from the digital invoice, where each entity extract from the digital invoice has a potential mapping to a trained machine learning model element. An entity extraction correction module overrides the potential mapping to the trained machine learning model element when user feedback from a similar entity extract from a previously processed digital invoice exists to produce a processed digital invoice with a user feedback element inconsistent with the potential mapping to the trained machine learning model element. The processed digital invoice is delivered to an accounting module for final disposition of the digital invoice.

Abstract: Disclosed embodiments provide techniques to identify the in-context meanings of natural language in order to decipher the evolution or creation of new vocabulary words and create a more holistic user experience. Thus, disclosed embodiments improve the technical field of digital content comprehension. In embodiments, machine learning is used to identify sentiment of text, perform entity detection to determine topics of text, and/or perform image analysis on images used in digital content. Words, symbols, and images that are determined to be potentially unfamiliar to a user are augmented with a supplemental definition indication. Invoking the supplemental definition indication enables rendering of additional definition information for the user. This serves to accelerate understanding of digital content such as webpages and social media posts.

Abstract: The present disclosure discloses a context-based multi-turn dialogue method.

Abstract: Methods and systems for multimodal conversational dialogue. The multimodal conversational dialogue system includes multiple sensors to detect multimodal inputs from a user. The multimodal conversational dialogue system includes a multimodal sematic parser that performs semantic parsing and multimodal fusion of the multimodal inputs to determine a goal of the user. The multimodal conversational dialogue system includes a dialogue manager that generates a dialogue with the user in real-time. The dialogue includes system-generated utterances that are used to conduct a conversation between the user and the multimodal conversational dialogue system.

Abstract: A method and system for identifying the beginning and ending of songs via a machine learning analysis. A machine learning model analyzes streaming audio (such as a radio broadcast) in overlapping, 3-second samples. Each sample is labeled into groups such as “song,” “talk,” “commercial” and “transition.” Based on the location of the transition samples, an exact second a given song begins and ends in the audio stream is derivable. The model further identifies when two songs shift between one another.

Abstract: A control method includes: calculating a correction value after a predetermined process is executed; and controlling a control target based on an output value of at least one of a real sensor and a virtual sensor during execution of the predetermined process. The calculating includes correcting an output value of the virtual sensor. The controlling includes: controlling the control target based on an output value of the real sensor while monitoring a failure of the real sensor; correcting an output value of the virtual sensor with the correction value when the real sensor fails; and switching from a control based on the output value of the real sensor to a control based on the output value of the virtual sensor after the correcting the output value of the virtual sensor.

Abstract: A machine translation system, a ChatOps system, a method for a context-aware language machine identification, and computer program product. One embodiment of the machine translation system may include a density calculator. The density calculator may be adapted to calculate a part of speech (POS) density for a plurality of word tokens in an input text, calculate a knowledge density for the plurality of word tokens, and calculate an information density for the plurality of word tokens using the POS density and the knowledge density. In some embodiments, the machine translation system may further comprise a sememe attacher and a context translator.

Abstract: A sound pickup device includes a plurality of microphone elements, a sensitivity correcting unit that corrects a difference in sensitivity among the microphone elements by multiplying an output signal of each of the microphone elements by a gain. The sound pickup device also includes a target sound detecting unit that detects a voice of a speaker as a target sound, a sensitivity correction control unit that controls the gain based on a result of detecting the target sound, and a directivity synthesizing unit that picks up the target sound in a boosted manner using the output signals from the microphone elements of which difference in sensitivity is corrected. The sensitivity correction control unit updates the gain based on the output signals from the microphone elements if the voice of the speaker is detected and does not update the gain if the voice of the speaker is not detected.

Abstract: From metadata of a corpus of natural language text documents, a relativity matrix is constructed, a row-column intersection in the relativity matrix corresponding to a relationship between two instances of a type of metadata. An encoder model is trained, generating a trained encoder model, to compute an embedding corresponding to a token of a natural language text document within the corpus and the relativity matrix, the encoder model comprising a first encoder layer, the first encoder layer comprising a token embedding portion, a relativity embedding portion, a token self-attention portion, a metadata self-attention portion, and a fusion portion, the training comprising adjusting a set of parameters of the encoder model.

Abstract: Techniques for sending prompt data related to content output on a voice-controlled device are described. In an example, a computer system receives request for audio output at a user device. The computer system determines a recommendation for content. The computer system also generates customization data for prompt data based on one or more user features, context features, metadata features, and a history of customization data. The prompt data includes the customization data and an acknowledgement associated with the request. The computer system sends the prompt data to the user device.

Abstract: Systems and methods are described for providing subtitles for a media content item. Subtitles are obtained, using control circuitry, for the media content item. Control circuitry determines whether a character component of the subtitles should be replaced by an image component. In response to determining that the character component of the subtitles should be replaced by an image component, control circuitry selects, from memory, an image component corresponding to the character component. Control circuitry replaces the character component of the subtitles by the image component to generate modified subtitles.

Abstract: System and method for aspect-level sentiment classification. The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to: receive a sentence having a labeled aspect term and context; convert the sentence into a dependency tree graph; calculate an attention matrix of the dependency tree graph based on one-hop attention between any two nodes of the graph; calculate multi-head attention diffusion for any two nodes from the attention matrix; obtain updated embedding of the graph using the multi-head diffusion attention; classify the aspect term based on the updated embedding of the graph to obtain predicted classification of the aspect term; calculate loss function based on the predicted classification and the ground truth label of the aspect term; and adjust parameters of models in the computer executable code based on the loss function.

Abstract: In one aspect, a system receives a request to cluster a set of log records. Responsive to receiving the request, the system identifies at least one dictionary that defines a set of tokens and corresponding token weights and generates, based at least in part on the set of tokens and corresponding token weights, a set of clusters such that each cluster in the set of clusters represents a unique combination of two or more tokens from the dictionary and groups a subset of log records mapped to the unique combination of two or more tokens. The system may then perform one or more automated actions based on at least one cluster in the set of clusters.

Abstract: Natural language elements are present in both the executable lines and non-executable lines of the code. Rich information hidden within them are often ignored in code analysis as extraction of meaningful insights from its raw form is not straight forward. A system and method extracting natural language elements from an application source code is provided. The disclosure provides a method for performing detailed analytics on the natural language elements, classify those using deep learning networks and create meaningful insights. The system understands the different type of natural language elements, comment patterns present in the application source code and segregates the authentic comments having valuable insights, version comments, data element level comments from other non-value adding comments.

Abstract: Disclosed are systems and methods for a frontend capture module of a video conferencing application, which can modify an input signal, received from a microphone device to match predetermined signal characteristics, such as voice signal level and expected noise floor. An Input stage, a suppression module and an output stage amplify the voice signal portion of the input signal and suppress the noise signal of input signal to predetermined ranges. The input stage selectively applies gains defined by a gain table, based on signal level of the input signal. The suppression module selectively applies a suppression gain to the input signal based on presence or absence of voice signal in the input signal. The output stage further amplifies the input signal in portions having a voice signal and applies a gain table to maintain a consistent noise floor.

Abstract: An audio spotting system configured for various operating modes including a regular mode and sensitivity mode is described. An example cascade audio spotting system may include a high-power subsystem including a high-power trigger and a transfer module. This high-power trigger includes one or more detection models used to detect whether a target sound activity is included in the one or more audio streams. The one or more detection models are associated with a first set of hyperparameters when the cascade audio spotting system is in a regular mode, and the one or more detection models are associated with a second set of hyperparameters when the cascade audio spotting system is in a sensitivity mode. The transfer module provides at least one of one or more processed audio streams for further processing in response to the high-power trigger detecting the target sound activity in the one or more audio streams.

Abstract: A computer system may connect to various customer-facing devices and manage or automate the order process between a retail store and the customer. The computer system may perform the dialogue and receive an order for items from the retail store and may perform quality control monitoring of the dialogue between customers and employees taking orders. The ordering system may utilize the ordered items in combination with various contextual cues to determine a customer identity which may then be linked to past orders and/or various order preferences. Based on the determined customer identity, the system may provide recommendations of additional order items or order alterations to the customer before personally identifying information has been collected from the customer. The determination of the customer identity and the determination of recommendations may be performed by machine learning algorithms that were trained on customer data and the retail store products.

Abstract: An apparatus for providing a processed audio signal representation on the basis of input audio signal representation configured to apply an un-windowing, in order to provide the processed audio signal representation on the basis of the input audio signal representation. The apparatus is configured to adapt the un-windowing in dependence on one or more signal characteristics and/or in dependence on one or more processing parameters used for a provision of the input audio signal representation.

Abstract: A method includes providing audio signals of an interaction between a plurality of human speakers, the speakers speaking into electronic devices to record the audio signals. The audio signals, which are optionally combined, include agent audio and subject audio. The method further includes automatically processing the audio signals to generate a speaker separated natural language transcript of the interaction from the audio signals. For each identified question, a subject response is identified. From the agent text, it is determined whether the question asked by the at least one agent is an open question or a closed question. A decision engine is used to determine the veracity of the subject response and the subject response is flagged if the indicia of the likelihood of deception in the subject response exceeds a predetermined value.