Abstract: A communication system (100) formed of a radio management system (104) interoperates with a radio management codeplug database (106) and a confusability analyzer (108) for the creation and storage of voice recognition target strings for uploading to one or more land mobile portable radios (110) prior to field-deployment. Once the radios are deployed to the field, unrecognized voice command entries are determined, stored locally at the portable radio, and uploaded to cloud based storage (122). Analysis of the cloud based data is performed through a voice control analytics engine (124) to detect patterns associated with the unrecognized voice commands. The unrecognized voice command pattern is processed though a resolution action engine (126) to generate one or more resolution actions for the pattern.

Abstract: The present application discloses a method, device, and system for data transmission. The system includes a first terminal having an associated terminal ID and a server. At least one of the first terminal and the server establishes a channel between the first terminal and the server based at least in part on the terminal ID, the channel corresponding to a communication channel that is to be used by the first terminal and the server to communicate data. The terminal ID is used to authenticate the first terminal in connection with the channel being established between the first terminal and the server.

Abstract: The invention relates to a method for entering commands into an electronic device with a touch-sensitive display unit on which an image can be displayed and at least an area of the displayed image can be selected by means of a pointer and in which segmentation can thereby be carried out in a targeted manner and with a speech recognition unit by means of the commands can be generated for the electronic device. According to the invention, the user of the electronic device selects at least a partial area of a displayed image, and the selected area is subjected to an image analysis following a simultaneous acoustic input.

Abstract: Methods of using a tool for improving language skills comprising selecting a language concept and then a word associated with the language concept; asking the patient to answer a question related to the language concept about the first word; scoring the patient's response to the based upon at least one or more of the following: the number of words given, the number of prompts the patient needed to be provided in order to illicit the first response, the amount of time the patient needed to produce the first response; and then moving the word to a first location, that physically represents to the patient the first word score they achieved. Further aspects involve calculating a total therapeutic session score by totaling up all the individual word scores from the therapeutic session and producing a therapeutic session report. As well as comparing results across sessions.

Abstract: As noted above, example techniques relate to toggling a cloud-based VAS between enabled and disabled modes. An example implementation involves a NMD detecting that the housing is in a first orientation and enabling a first mode. Enabling the first mode includes disabling voice input processing via a cloud-based VAS and enabling local voice input processing. In the first mode, the NMD captures sound data associated with a first voice input and detects, via a local natural language unit, that the first voice input comprises sound data matching one or more keywords. The NMD determines an intent of the first voice input and performs a first command according to the determined intent. The NMD may detect that the housing is in a second orientation and enables the second mode. Enabling the second mode includes enabling voice input processing via the cloud-based VAS.

Abstract: There is disclosed in one example a computing apparatus, including: a processor; and logic encoded into one or more computer-readable mediums, the logic to instruct the processor to: capture first data from an intermediate data source across a first temporal interval; perform partial signal processing on the first data to classify the first temporal interval as either suspicious or not suspicious, wherein the first temporal interval is classified as suspicious if it is determined to potentially represent at least a portion of a cryptomining operation; classify second through N temporal intervals as either suspicious or not suspicious; based on the first through N temporal intervals, classify the apparatus as either operating a cryptomining function or not; and upon classifying the apparatus as operating a cryptomining function and determining that the cryptomining function is not authorized, take remedial action on the apparatus.

Abstract: Technologies for natural language interactions with virtual personal assistant systems include a computing device configured to capture audio input, distort the audio input to produce a number of distorted audio variations, and perform speech recognition on the audio input and the distorted audio variants. The computing device selects a result from a large number of potential speech recognition results based on contextual information. The computing device may measure a user's engagement level by using an eye tracking sensor to determine whether the user is visually focused on an avatar rendered by the virtual personal assistant. The avatar may be rendered in a disengaged state, a ready state, or an engaged state based on the user engagement level. The avatar may be rendered as semitransparent in the disengaged state, and the transparency may be reduced in the ready state or the engaged state. Other embodiments are described and claimed.

Abstract: An information processing apparatus including an output control unit that controls display of a user interface related to a recognition application. The output control unit causes a visual effect to be output to an input field to which a recognition result is input, the visual effect indicating a state related to recognition. Also provided is an information processing method including controlling, by a processor, display of a user interface related to a recognition application. Controlling of the display further includes causing a visual effect to be output to an input field to which a recognition result is input, the visual effect indicating a state related to recognition.

Abstract: Methods, systems, apparatus, including computer programs encoded on a computer storage medium, for a user device to learn offline voice actions. In one aspect, the method includes actions of detecting, by the user device, an utterance at a first time when the user device is connected to a server by a network, providing, by the user device, the utterance to the server using the network, receiving, by the user device and from the server, an update to the grammar of the user device, detecting, by the user device, a subsequent utterance of the utterance at a second time when the user device is not connected to the server by a network, and in response to detecting, by the user device, the subsequent utterance of the utterance at the second time, identifying, by the user device, an operation to perform based on (i) the subsequent utterance, and (ii) the updated grammar.

Abstract: Various embodiments enable a user editing a document to tag product references in the document. These product references can then be recognizable when the document is published online, thereby enabling ad units (or other personalized units associated with the content) to be inserted either at a location associated with a particular product reference or within the document in a designated location. For example, when editing or drafting a document, a client-side tool could enable a user to tag particular words within the text to create a hyperlink to product pages of an electronic marketplace. In another example, a client-side tool could auto-insert a list of words associated with subject matter of the same. Accordingly, mentions of these words in content could be auto-converted into text-links or hyperlinks to a respective items page of the electronic marketplace.

Abstract: A system (100) for enabling a user to select media content in an entertainment environment, comprising a remote control device (110) having a set of user-activated keys and a speech activation circuit adapted to enable a speech signal; a speech engine (160) comprising a speech recognizer (170); an application wrapper (180) configured to recognize substantive meaning in the speech signal; and a media content controller (190) configured to select media content. Every function that can be executed by activation of the user-activated keys can also be executed by the speech engine (160) in response to the recognized substantive meaning.

Abstract: A device includes a screen and one or more processors configured to provide, at the screen, a graphical user interface (GUI) configured to display data associated with multiple devices on the screen. The GUI is also configured to illustrate a label and at least one control input for each device of the multiple devices. The GUI is also configured to provide feedback to a user. The feedback indicates that a verbal command is not recognized with an action to be performed. The GUI is also configured to provide instructions for the user on how to teach the one or more processors which action is to be performed in response to receiving the verbal command.

Abstract: The present disclosure provides a content recognizing method and apparatus, a device and a computer storage medium, wherein the method comprises: a smart multimedia device performing speech recognition and intention parsing for a speech instruction; if a content recognition intention is obtained from the parsing, internally recording multimedia content that is being played by the smart multimedia device; sending internally-recorded media data to a server side, and obtaining a content recognition result returned by the server side for the media data. The user may implement recognition of multimedia content through speech interaction with the smart multimedia device, and operations are simple without depending on other smart devices.

Abstract: Aspects of the disclosure provide an information processing apparatus that includes interface circuitry and processing circuitry. The interface circuitry is configured to obtain a text authored by a person. The processing circuitry is configured to analyze the text to obtain measurements of language features of the person, input the measurements of the language features into an evaluation model that is trained to predict a score as a function of the language features, determine a specific score for the person based on the evaluation model and output the specific score of the person for predicting a behavior of the person.

Abstract: A printing system includes a server system to receive instruction data based on a voice instruction accepted by a voice control device and transmit message data, and a printing apparatus that communicates with the server system. The voice control device outputs, in a case where the message data for narrowing down content to be printed is transmitted, a message by voice based on the transmitted message data and accepts a voice instruction related to a content of the first content type, the server system specifies content data of the first content type based on instruction data received in a case where the voice instruction related to the content of the first content type is accepted, and the printing apparatus executes printing based on print data generated based on the specified content data of the first content type.

Abstract: A cognitive system collects online behaviors of a user and an affinity group of users who are related (e.g. by relationship, or behavioral similarities) to the user. A knowledge base of behavior and sentiment patterns is produced and maintained. If real-time data for the user shifts in behavior and/or sentiment and significantly deviates from established patterns, the system looks for a similar behavior and/or sentiment pattern shift among members of the affinity group. If the affinity group patterns shift in a manner similar to the first user's pattern shift, the cognitive system, in response, updates the knowledge base with information related to the shift, thereby adding knowledge to the long-term patterns. If the cognitive system finds that the user's behavior and/or sentiment pattern shift differs significantly from the affinity group, the system generates an empathy fostering alert message and sends it to one or more recipients.

Abstract: A method, an electronic device, and a non-transitory computer-readable recording medium are provided for voice recognition. The method includes method of performing voice recognition by an electronic device including a first voice recognition device and a second voice recognition device, the method comprising receiving first voice by one of first voice recognition device and second voice recognition device; when first voice is received by the first voice recognition device and the first voice recognition device recognizes a predetermined command in the first voice, transferring a received second voice to an external electronic device and recognizing the received second voice through the external electronic device; and when the first voice is received by the second voice recognition device and the second voice recognition device recognizes the predetermined command in the first voice, recognizing a second command in the received second voice, and performing an operation based on the recognized second command.

Abstract: A system and method for assisting communication through predictive speech is provided. A database includes commonly used words, phrases, and images, each associated with at least one context cue. A processor is configured to determine the user's context and display a number of possible initial words, phrases, or images associated with the determined context. A text field is updated with selected words, phrases, or images. The words, phrases, or literal equivalents of the images are audibly transmitted.

Abstract: The present disclosure is generally directed to the generation of voice-activated data flows in interconnected network. The voice-activated data flows can include input audio signals that include a request and are detected at a client device. The client device can transmit the input audio signal to a data processing system, where the input audio signal can be parsed and passed to the data processing system of a service provider to fulfill the request in the input audio signal. The present solution is configured to conserve network resources by reducing the number of network transmissions needed to fulfill a request.

Abstract: A method for generating training data for training a natural language processing system comprises loading, into a computer memory, a computer-readable transcript representing an ordered sequence of one or more dialogue events. The method further comprises acquiring a computer-readable command describing an exemplary ordered subsequence of one or more dialogue events from the computer-readable transcript. The method further comprises re-parametrizing the computer-readable command with an alternative semantic parameter. The method further comprises generating an alternative ordered subsequence of one or more dialogue events based on the re-parametrized computer-readable command. The method further comprises outputting, to a data store, an alternative computer-readable transcript including the alternative ordered subsequence of one or more dialogue events, the alternative computer-readable transcript having a predetermined format usable to train the computerized assistant.

Abstract: The present disclosure generally relates to a computer-implemented system for intelligently retaining and recalling memory data. An exemplary method comprises receiving, via a microphone of an electronic device, a speech input of the user; receiving a text input of the user; constructing a first instance of a memory data structure based on the speech input; constructing a second instance of the memory data structure based on the text input; adding the first instance and the second instance of the memory data structure to a memory stack of the user; obtaining one or more sentences entered into a document in a text processing application; retrieving a particular instance of the memory data structure from the memory stack based on the one or more sentences; generating a proposed sentence based on the particular instance of the memory data structure; and causing display of the proposed sentence in the text processing application.

Abstract: A media guidance application may monitor a conversation among users, and identify keywords in the conversation, without the use of wakewords. The keywords are used to search for media content that is relevant to the on-going conversation. Accordingly, the media guidance application presents relevant content to the users, during the conversation, to more actively engage the users. A conversation monitoring window may be used to present conversation information as well as relevant content. A listening mode may be used to manage when the media guidance application processes speech from a conversation. The media guidance application may access user profiles for keywords, select content types, select content sources, and determine relevancy of media content, to provide content in context of a conversation.

Abstract: An improved translation experience is provided using an auxiliary device, such as a pair of earbuds, and a wirelessly coupled mobile device. Microphones on both the auxiliary device and the mobile device simultaneously capture input from, respectively, a primary user (e.g., wearing the auxiliary device) and a secondary user (e.g., a foreign language speaker providing speech that the primary user desires to translate). Both microphones continually listen, rather than alternating between the mobile device and the auxiliary device. Each device may determine when to endpoint and send a block of speech for translation, for example based on pauses in the speech. Each device may accordingly send the received speech for translation and output, such that it is provided in a natural flow of communication.

Abstract: Techniques that facilitate generating and executing an optimal dialogue strategy are provided. In one example, a system includes an information gain component and a question selector component. The information gain component estimates information gain data associated with first dialogue data of an information system. The information gain data is indicative of an amount of change in entropy associated with the first dialogue data. The question selector component selects between second dialogue data associated with a first question strategy and third dialogue data associated with a second question strategy based on the information gain data.

Abstract: A method for generating a dialogue event in a natural language processing system comprises loading, into a computer memory, a computer-readable seed command describing an ordered sequence of two or more top-level dialogue events. A dialogue event includes a client utterance or a computerized assistant response. The seed command includes one or more sub-commands, each sub-command corresponding to a portion of the ordered sequence of two or more top-level dialogue events, and the focal sub-command of the one or more sub-commands being parametrized by a seed semantic parameter. The method further comprises re-parametrizing the focal sub-command by outputting a plurality of different re-parametrized focal sub-commands wherein, in each re-parametrized focal sub-command, the seed semantic parameter is replaced by one of a plurality of different synthetic semantic parameters.

Abstract: A method for speech emotion recognition for enriching speech to text communications between users in speech chat sessions including: implementing a speech emotion recognition model to enable converting observed emotions in speech samples to enrich text with visual emotion content by: generating a data set of speech samples with labels of a plurality of emotion classes; extracting a set of acoustic features from each of the emotion classes; generating a machine learning (ML) model based on the acoustic features and data set; training the ML model from acoustic features from speech samples during speech chat sessions; predicting emotion content based on a trained ML model in the observed speech; generating enriched text based on predicted emotion content of the trained ML model; and presenting the enriched text in speech to text communications between users in the chat session for visual notice of an observed emotion in the speech sample.

Abstract: A system for autonomously photographing wildlife includes a camera apparatus, camera mount and actuating unit. The camera apparatus records video data may include a camera, a memory and a processing system which includes a processor and an image analysis module including computer executable instructions stored in the memory. The image analysis module receives a video data file; performs an image analysis of discrete portions of the video data file; detects motion within each respective discrete portion; determines whether the detected motion is caused by an animal; calculates an outline for the animal; and stores a selected discrete portion of the video data file in the memory. The selected discrete portion includes an outline of the animal. The camera mount receives the camera thereon and the actuating unit couples the camera to the camera mount and is actuatable to tilt and/or pan the camera.

Abstract: Processor(s) of a client device can: identify a textual segment stored locally at the client device; process the textual segment, using a speech synthesis model stored locally at the client device, to generate synthesized speech audio data that includes synthesized speech of the identified textual segment; process the synthesized speech, using an on-device speech recognition model that is stored locally at the client device, to generate predicted output; and generate a gradient based on comparing the predicted output to ground truth output that corresponds to the textual segment. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

Abstract: A method for natural language interaction includes recording speech provided by a human user. The recorded speech is translated into a machine-readable natural language input relating to an interaction topic. An interaction timer is maintained that tracks a length of time since a last machine-readable natural language input referring to the interaction topic was translated. Based on a current value of the interaction timer being greater than an interaction engagement threshold, a message relating to the interaction topic is delivered with a first natural language phrasing that includes an interaction topic reminder. Based on the current value of the interaction timer being less than the interaction engagement threshold, the message relating to the interaction topic is delivered with a second natural language phrasing that lacks the interaction topic reminder.

Abstract: A call challenger can receive a user input from a called party identity to opt-in to a call challenge service, and a second user input of a keyword. When the call challenger receives a call directed to a user equipment of the called party identity, the call challenger can prompt the calling party to provide an audible response. In response to a receipt of the audible response, the call challenger can convert the audible response to a text. The call challenger can compare the text with the keyword to determine if there is a sufficient match. In response to the determining the output of the comparing does not satisfy a threshold match score, the call challenger can prevent the call from connecting with the user equipment.

Abstract: A user-customized method, system and computer program for automated translation from a source language and a target language. The user's native language and accent are detected, from which a set of phonemes is determined which are those that are difficult to pronounce for that user based on his or her native language and accent. A translation engine is applied to translate a fragment of the source language input into target language output, wherein the translation is performed with reference to the synonym database for the target language so as to preferentially avoid word strings in the output that contain phonemes that exist in the user's set of difficult-to-pronounce phonemes.

Abstract: The present disclosure describes a conversation facilitation system for facilitating conversation-based social interactions to improve senior health, one or more operations and functions being efficiently achieved via this system comprise: receiving a dialog act of a conversation, applying natural language understanding (NLU) processing on the dialog act, computing a conversation metric, and generating a result of the conversation to conclude the conversation based on the conversation metric.

Abstract: Embodiments of the present invention describe an approve for ledger synchronization. Embodiments monitor conversations for keywords, and responsive to detecting the keywords, recording at least a portion of the conversations that includes the keywords. Additionally, embodiments store recorded conversation, based on the at least portion of the conversations that include the keywords, in a database, detect changes to ledgers, and determine authorization records is absent on the ledgers for the changes. Furthermore, embodiments, determine at least one of the stored conversations includes authorization records associated with the detected changes, retrieve the determined at least one of stored conversations, and synchronize the ledgers by creating a new block to the ledgers indicating authorization for the new block based on the determined at least one of stored conversations.

Abstract: An audio processing system is described for an audio event detection (AED) system. The system includes a feature extraction block configured to derive at least one feature which represents a spectral feature of the input signal.

Abstract: Systems and methods for media playback via a media playback system include capturing sound data via a network microphone device and identifying a candidate wake word in the sound data. Based on identification of the candidate wake word in the sound data, the system selects a first wake-word engine from a plurality of wake-word engines. Via the first wake-word engine, the system analyzes the sound data to detect a confirmed wake word, and, in response to detecting the confirmed wake word, transmits a voice utterance of the sound data to one or more remote computing devices associated with a voice assistant service.

Abstract: The present disclosure generally relates to a computer-implemented system for intelligently retaining and recalling memory data. An exemplary method comprises receiving, via a microphone of an electronic device, a speech input of the user; receiving a text input of the user; constructing a first instance of a memory data structure based on the speech input; constructing a second instance of the memory data structure based on the text input; adding the first instance and the second instance of the memory data structure to a memory stack of the user; displaying a user interface for retrieving memory data of the user; receiving, via the user interface, a beginning of a statement from the user; retrieving a particular instance of the memory data structure from the memory stack based on the beginning of the statement; and automatically displaying a completion of the statement.

Abstract: Examples of techniques for augmented reality authoring using virtual reality are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method includes receiving, by a virtual reality processing system, a depth map from an augmented reality processing system, wherein the depth map is a map of a scene. The method further includes authoring, using the virtual reality processing system, an augmented reality experience in a virtual reality environment based at least in part on the depth map. The method further includes transmitting, by the virtual reality processing system, the augmented reality experience to the augmented reality processing system.

Abstract: A system includes a robot having a module that includes a function for mapping natural language commands of varying complexities to reward functions at different levels of abstraction within a hierarchical planning framework, the function including using a deep neural network language model that learns how to map the natural language commands to reward functions at an appropriate level of the hierarchical planning framework.

Abstract: An information processing device including a control unit which, on a basis of a positional relation between a generation source of noise and a sound collecting unit that collects a sound generated by a user, controls output to induce an action of the user to change a sound collection characteristic of a generated sound, the action being different from an operation related to processing of the sound collecting unit. An information processing method performed by a processor, the information processing method including, on a basis of a positional relation between a generation source of noise and a sound collecting unit that collects a sound generated by a user, controlling output to induce an action of the user to change a sound collection characteristic of a generated sound, the action being different from an operation related to processing of the sound collecting unit.

Abstract: Systems and methods for enhancing search results for improved readability are provided. A search result is identified using a set of query terms. The search result may be first-party content or third-party content. The search result includes a first textual portion and a second textual portion. Each of the set of query terms that appear in the first textual portion are highlighted in the first textual portion. Each of the set of query terms that appear in the second textual portion but not in the first textual portion are highlighted in the second textual portion. A query response including the highlighted search result is generated and provided to a client device.

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

Abstract: An electronic apparatus is provided, which includes a display configured to display notification information, a memory configured to store a notification display option of an application that generates the notification information, and a processor configured to control the display to display the notification information based on the notification display option of the application, wherein, when an interaction regarding the notification information is generated, the processor is configured to change the notification display option of the application stored in the memory based on a type of the interaction.

Abstract: Interface and mode selection for digital action execution is provided. For example, a system loads a script library embedded in an electronic resource. The system determines a historic level of engagement between a client computing device and one or more digital assistants. The system selects, based on a first property of the client computing device and the historic level of engagement, a type of digital interface. The system generates, based on the type of digital interface, a digital interface with the call-to-action. The system determines, responsive to an instruction to execute the call-to-action, a mode of execution. The system selects a digital assistant and a second client device to execute the call-to-action. The system transmits the call-to-action to the second client device for execution.

Abstract: In certain implementations, a system for facilitating voice commerce is provided. A user input comprising a natural language utterance related to a product or service to be purchased may be received. A first product or service that is to be purchased may be determined based on the utterance. First payment information that is to be used to purchase the first product or service may be obtained. First shipping information that is to be used to deliver the first product or service may be obtained. A purchase transaction for the first product or service may completed based on the first payment information and the first shipping information without further user input, after the receipt of utterance, that identifies a product or service type or a product or service, seller information, payment information, shipping information, or other information related to purchasing the first product or service.

Abstract: Electronic records are accessed from computer storage for a given subject, wherein the electronic records include natural language notes about the subject. Tokens are identified in the natural language notes. For each token, a corresponding intensity score is generated representing an intensity of match between the token and a particular dimension, wherein the intensity scores are each values on a first scale, wherein each dimension is one of a plurality of dimensions of a category out of a plurality of categories; generating rescaled-intensity scores from the intensity scores by rescaling the intensity scores from the first scale to a second scale different from the first scale. For each dimension of each category, a dimension-score is compiled based on the intensity scores; and categorizing the subject into at least one category based on the dimension scores. The subject is categorized into at least one category based on the dimension scores.

Abstract: Machine learning models are powerful artificial intelligence tools that can make determinations based on a variety of factors. Unlike a simple linear model, however, determining the contribution of each variable to the outcome of a machine learning model is a challenging task. It may be unclear which factors contributed heavily toward a particular outcome of the machine learning model and which factors did not have a major effect on the outcome. Being able to accurately determine the underlying causative factors for a machine learning-based decision, however, can be important in several contexts. The present disclosure describes techniques that allow for training and use of non-linear machine learning models, while also preserving causal information for outputs of the models. Relative weight calculations for machine learning model variables can be used to accomplish this, in various embodiments.

Abstract: A computing system may include persistent storage and a software application. The persistent storage may contain (i) pre-defined conversation flows respectively corresponding to conversation topics and (ii) pre-defined mappings that respectively associate the conversation topics to conversational expression(s) with matching semantic meanings.

Abstract: Systems and methods for scoring spoken Chinese are provided. In an exemplary method, a user reads a written transcript and the user's voice is recorded. Characters of the transcript are then represented as pinyins with tone markings. The voice recording is sectioned into individual phonemes that are aligned with the phonemes of the pinyins. For each character of the transcript, a tone is determined for the phonemes in the voice recording corresponding to that character. That tone is scored as correct or incorrect by comparison to the tone marking associated with the pinyins for that character. The pronunciation of each phoneme of the voice recording is also scored relative to the corresponding phonemes of the pinyins of the characters of the transcript. Further scores for words and sentences can be developed from the tone and pronunciation scores and provided to the user with feedback.

Abstract: Systems, methods, and software to provide intelligent detection and automatic correction of erroneous audio settings in a video conference. Electronic conferences can often be the source of frustration and wasted resources as participants may be forced to contend with extraneous sounds, such as background/ambient noises, or conversations not intended for the conference, provided by an endpoint that should be muted. Similarly, participants may speak with the intention of providing their speech to the conference while their associated endpoint is muted. As a result, the conference may be awkward and lack a productive flow while endpoints are erroneously muted or non-muted. By intelligently processing at least the video portion of a video conference, endpoints/participants may be prompted to mute/unmute or automatically muted/unmuted.

Abstract: A method, system, and computer readable storage medium for managing computer memory by an intelligent memory manager. The intelligent memory manager performs a method including: initializing a memory allocator within an intelligent memory manager in a computing system; allocating, by the memory allocator, a plurality of main memory objects; backing up, with the intelligent memory manager, at least one main memory object in the plurality of main memory objects in a persistent storage utilizing a backup operation; monitoring, with the intelligent memory manager, input-output bandwidth being consumed for storing information in the persistent storage; and modifying, with the intelligent memory manager, the backup operation based on monitoring the bandwidth being consumed.