Abstract: The present disclosure discloses a comment information processing method and apparatus, and a medium. The specific implementation solution is: in response to a user operation, determining an opinion category corresponding to each opinion phrase in a comment opinion dictionary; obtaining a target corpus matching each opinion phrase from a plurality of comment corpora; for each opinion phrase, using a corresponding opinion category to label the target corpus matching each opinion phrase to obtain a first training sample; and training a classification model with the first training sample to identify the opinion category of a comment by using a trained classification model.

Abstract: Selecting audio noise reduction models for noise suppression in an information handling system (IHS), including performing calibration and configuration of an audio noise reduction selection model, including: identifying contextual data associated with contextual inputs to the IHS; training, based on the contextual data, the audio noise reduction selection model, including generating a configuration policy including configuration rules, the configuration rules for performing actions for selection of a combination of audio noise reduction models to reduce combinations of noise sources associated with the IHS; performing steady-state monitoring of the IHS, including: monitoring the contextual inputs of the IHS, and in response, accessing the audio noise reduction selection model, identifying configuration rules based on the monitored contextual inputs, applying the configuration rules to select a particular combination of audio noise reduction models, applying particular combination of audio noise reduction mod

Abstract: Techniques are described herein for training and evaluating machine learning (ML) models for document processing computing applications based on in-domain and out-of-domain characteristics. In some embodiments, an ML system is configured to form feature vectors by mapping unknown tokens to known tokens within a domain based, at least in part, on out-of-domain characteristics. In other embodiments, the ML system is configured to map the unknown tokens to an aggregate vector representation based on the out-of-domain characteristics. The ML system may use the feature vectors to train ML models and/or estimate unknown labels for the new documents.

Abstract: Techniques are described herein for training and evaluating machine learning (ML) models for document processing computing applications based on in-domain and out-of-domain characteristics. In some embodiments, an ML system is configured to form feature vectors by mapping unknown tokens to known tokens within a domain based, at least in part, on out-of-domain characteristics. In other embodiments, the ML system is configured to map the unknown tokens to an aggregate vector representation based on the out-of-domain characteristics. The ML system may use the feature vectors to train ML models and/or estimate unknown labels for the new documents.

Abstract: Disclosed are a method for coding a residual signal of LPC coefficients based on collaborative quantization and a computing device for performing the method. The residual signal coding method includes: generating encoded LPC coefficients and LPC residual signals by performing LPC analysis and quantization on an input speech; Determining a predicted LPC residual signal by applying the LPC residual signal to cross module residual learning; Performing LPC synthesis using the coded LPC coefficients and the predicted LPC residual signal; It may include the step of determining an output speech that is a synthesized output according to a result of performing the LPC synthesis.

Abstract: Systems, methods, apparatuses, and computer-readable media for categorized text determination and organization are described. In one embodiment, an apparatus may include a processor and a memory storing instructions which when executed by the processor cause the processor to determine a plurality of contextual text elements in at least one text source, combine the plurality of contextual text elements, classify events associated with at least a portion of the plurality of contextual text elements, and determine text elements related to at least a portion of the contextual text elements. Other embodiments are described.

Abstract: A system described herein may provide a technique for the use of machine learning techniques to perform authentication, such as biometrics-based user authentication. For example, user biometric information (e.g., facial features, fingerprints, voice, etc.) of a user may be used to train a machine learning model, in addition to a noise vector. A representation of the biometric information (e.g., an image file including a picture of the user's face, an encoded file with vectors or other representation of the user's fingerprint, a sound file including the user's voice, etc.) may be iteratively transformed until the transformed biometric information matches the noise vector, and the machine learning model may be trained based on the set of transformations that ultimately yield the noise vector, when given the biometric information.

Abstract: A language understanding system is configured to process utterances to predict intents of users, including by suggesting utterances and intents based on searches performed by one or more microservices. A central service is configured to receive inputs/queries from a user, to communicate with a plurality of language processing microservices, and to return a response to the user. The microservices may be configured to apply respective search algorithms comparing the input to respective data sources such as databases, indexes, or knowledge graphs. The microservices may rate utterances and/or entities in the respective data sources with respect to the input. The one or more microservices may generate a ranked list and return the ranked list to the central service. The central service may then apply a secondary rating/ranking algorithm in order to select one or more predicted utterances and/or entities to return to the user based on the initial user input.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for evaluating a translation quality. The method may include: acquiring a to-be-evaluated translation and a reference translation; inputting the to-be-evaluated translation and the reference translation into a pre-trained repetition coding model to obtain a semantic similarity between the to-be-evaluated translation and the reference translation, the repetition coding model being a neural network for calculating a probability of a pair of sentences being repetition sentences; analyzing the to-be-evaluated translation and the reference translation into two syntax trees respectively; calculating a similarity between the two syntax trees as a text similarity between the to-be-evaluated translation and the reference translation; and using a weighted sum of the semantic similarity and the text similarity as a translation quality score.

Abstract: The present disclosure provides a method and a device of denoising a voice signal. The method portion includes the following steps: filtering out an environmental noise signal in an original input signal according to an interference signal related to the environmental noise signal in the original input signal to obtain a first voice signal; obtaining a sample signal matching the first voice signal from a voice signal sample library; and filtering out other noise signal in the first voice signal according to the sample signal matching the first voice signal, to obtain an effective voice signal. The method provided by the present disclosure may effectively filter out the environmental noise signal and other noise signal in the voice signal.

Abstract: Techniques for generation of synthetic queries from customer data for training of document querying machine learning (ML) models as a service are described. A service may receive one or more documents from a user, generate a set of question and answer pairs from the one or more documents from the user using a machine learning model trained to predict a question from an answer, and store the set of question and answer pairs generated from the one or more documents from the user. The question and answer pairs may be used to train another machine learning model, for example, a document ranking model, a passage ranking model, a question/answer model, or a frequently asked question (FAQ) model.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. The speech recognition platform, in combination with the device, may therefore facilitate efficient interactions between the user and a voice-controlled device.

Abstract: The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining an input text, the input text comprising a source text; obtaining a placeholder of an ith word to be predicted in a target text; obtaining a vector representation of the ith word to be predicted, in which the vector representation of the ith word to be predicted is obtained by calculating the placeholder of the ith word to be predicted, the source text and 1st to (i?1)th predicted words by employing a self-attention mechanism; and generating an ith predicted word based on the vector representation of the ith word to be predicted, to obtain a target text.

Abstract: There are disclosed apparatus and methods for encoding and/or decoding information signals (e.g., audio signals). An encoder apparatus includes a plurality of frequency domain (FD) encoder tools for encoding an information signal, and an encoder bandwidth detector and controller configured to select a bandwidth for at least a subgroup of the FD encoder tools. The subgroup includes less FD encoder tools than the plurality of FD encoder tools. The selection is based on information signal characteristics, so that one of the FD encoder tools of the subgroup has a different bandwidth with respect to at least one of the FD encoder tools which are not in the subgroup.

Abstract: A method and system for providing an application-specific embedding for an entire text-to-content suggestions service is disclosed. The method includes accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an unsupervised ML model to the dataset to generate a pretrained embedding; and utilizing the pretrained embedding to train the text-to-content suggestion ML model utilized by the application.

Abstract: Techniques for generating natural language text with a natural language generation (NLG) system using a plurality of semantic objects including a first semantic object. The techniques include: obtaining a first specification of the first semantic object, the first specification specifying a first set of one or more data variables, first attributes, a first vocabulary, and a first document structure configuration; obtaining, from at least one data store, first data related to the first set of data variables; determining values of at least some of the first set of data variables using the first data; generating the natural language text including first natural language text, using the first specification, the values of at least some of the first set of data variables; and outputting the generated natural language text.

Abstract: Method and system for training a text-to-content suggestion ML model include accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an ML model to the dataset to generate a pretrained embedding, and applying a supervised ML model to a labeled dataset to train the text-to-content suggestion ML model utilized by the application by utilizing the pretrained embedding generated by the supervised ML model.

Abstract: Methods and systems are disclosed for detecting threats in voice communications such as telephone calls. Various voice phishing (vishing) detectors detect respective type of threats and can be used or activated individually or in various combinations. A tampering detector utilizes deep scattering spectra and shifted delta cepstra features to detect tampering in the form of voice conversion, speech synthesis, or splicing. A content detector predicts a likelihood that word patterns on an incoming voice signal are indicative of a vishing threat. A spoofing detector authenticates or repudiates a purported speaker based on comparison of voice profiles. The vishing detectors can be provided as an authentication service or embedded in communication equipment. Machine learning and signal processing aspects are disclosed, along with applications to mobile telephony and call centers.

Abstract: An apparatus for generating an error concealment signal, includes: an LPC representation generator for generating a replacement LPC representation; an LPC synthesizer for filtering a codebook information using the replacement LPC representation; and a noise estimator for estimating a noise estimate during a reception of good audio frames, wherein the noise estimate depends on the good audio frames representation generator is configured to use the noise estimate estimated by the noise estimator in generating the replacement LPC representation.

Abstract: A signal analysis device includes a memory and processing circuitry coupled to the memory and configured to obtain, for a spatial covariance matrix Rj (j is an integral number equal to or larger than 1 and equal to or smaller than J) for modeling spatial characteristics of J (J is an integral number equal to or larger than 2) source signals that are present in a mixed manner, a simultaneous decorrelation matrix P as a matrix in which all PHRjP are diagonal matrices, or/and Hermitian transposition PH thereof, as a parameter for decorrelating components corresponding to the J source signals for observation signal vectors based on observation signals acquired at I (I is an integral number equal to or larger than 2) different positions.