Abstract: According to an aspect, there is provided systems and methods to drive a conversation with a user. The method includes receiving conversational data from a user, embedding the conversational data, generating a reply using a response-generating AI to process the embedded conversational data and context from the knowledge base with the foundational model (e.g., LLM, multimodal, world model), and transmitting the generated reply.

Abstract: Natural language communications may be automated using language models and session contexts. A first session context may be created for communications between a language model and a first entity. Prompts may be generated using this session context, and responses from the language model may be used to communicate with the first entity. A second session context may also be created for communications between a language model and a second entity. Context transfer information may be generated by processing the first session context with a language model. The context transfer information may be added to the second session context. The second session context with the context transfer information may then be used to generate a communication to the second entity using a language model.

Abstract: Various embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to accurately and concisely generate one or more action item logs of one or more document data objects. For example, certain embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to generate an action item log of a document data object comprising one or more semantically complete or incomplete units of text data, by generating content segmentation units, determining action item presence predictions, generating action item sets from each content segmentation unit within a candidate action item subset, aggregating the action item sets to create an action item log, and storing the action item log.

Abstract: Systems and methods are presented for efficient cross-fading of compressed domain information streams on a user/client device. Exemplary systems may provide cross-fade between AAC/Enhanced AAC Plus information streams, between MP3 information streams, or between information streams of unmatched formats. These systems are distinguished in that cross-fade is directly applied to compressed bitstreams so a single decode operation is performed on the resulting bitstream. Thus, a set of frames from each input stream associated with the time interval in which a cross fade is decoded, and combined and recoded with a cross fade or other effect now in the compressed bitstream. Once sent through the client device's decoder, the user hears the transitional effect. The only input data that is decoded and processed is that associated with the portion of each stream used the crossfade, blend or other interstitial, and thus the vast majority of input streams are left compressed.

Abstract: Provided is a voice assistance system with proactive routines that couples a remote server and respective user voice interactive devices to deliver a complete experience to the end user of the device. The voice assistance system can also provide a platform to connect remote users to customize commands (e.g., proactive or reactive) to improve day-to-day operation across groups of devices and/or users. For example, routines can be built for an organization and made available to voice interactive devices distributed by or on behalf of the organization. Administrators can select features for the device and pre-configure voice assistance devices with groups of pre-selected routines to deliver a device that is ready to go out of the box. Updates to a device or routines can be based on such groups. Additionally, primary routine instances can be linked to groups where changes to the primary instance are propagated to any linked users.

Abstract: A technique translates speech in a first language to text in a second language manner in a manner that is appropriate for the gender of the speaker. In some implementations, the technique receives an input setting that specifies one of three translation modes: masculine mode, feminine mode, and auto mode. The first two modes produce translations in masculine and feminine modes by default, respectively, while the auto mode produces translations in forms that are based on the detected characteristics of audio signals. According to some implementations, the technique uses a training framework that automatically converts a corpus of training examples that exhibit gender bias (e.g., a male gender bias) to training examples having a reducing incidence of gender bias. In some implementations, the training framework updates weights of the machine-trained model based on a combination of two loss components: translation loss and gender loss.

Abstract: Approaches for determining continuous confidence scores for rule-based negation detection systems overcome deficiencies of existing rule-based negation detection systems that provide only binary output (e.g., negated or not negated). The approaches encompass a pointwise mutual information (PMI)-based approach in which PMI is measured between negation cue words and gold-standard negation annotations in a reference dataset. The approaches also encompass a conditional probability-based approach in which the condition probabilities that gold-standard negations exist in a reference dataset for negation cue words are measured. In both approaches, a form of association between negation cue words and gold-standard negations are measured to provide a more accurate indication of the rule-based system's confidence in a negation determination compared to a binary output.

Abstract: The control device includes a control unit. The control unit recognizes a voice command transmitted from a telephone terminal outside the vehicle. The control unit interprets the operation content requested by the recognized voice command. The control unit selects one or more positions at which the sound is picked up by the microphone in the vehicle cabin based on the interpreted operation content. The control unit picks up a voice uttered at one or more selected positions by a microphone and transmits the picked up voice to a telephone terminal.

Abstract: A device may be configured to parse a syntax element specifying the number of available languages within a presentation associated with an audio stream. A device may be configured to parse one or more syntax elements identifying each of the available languages and parse an accessibility syntax element for each language within the presentation.

Abstract: A method and an apparatus are disclosed for a speaker verification. The apparatus may comprise at least one processor configured to execute instructions to perform generating, based on an utterance of a speaker to a deep learning-based speaker verification model, a speaker embedding with a preset dimension, verifying, based on the speaker embedding, the speaker, and detecting, based on the verified speaker, an identity of a user associated with the apparatus.

Abstract: Methods and systems for processing of voice input to identify intents and mapped standard terminologies are provided. Using natural language processing, an intent of a voice input is identified. The intent is utilized to identify a standard terminology that maps to the intent. The standard terminology is utilized to identify information relevant to the standard terminology in a patient's electronic health record.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for receiving a voice query at a mobile computing device and generating data that represents content of the voice query. The data is provided to a server system. A textual query that has been determined by a speech recognizer at the server system to be a textual form of at least part of the data is received at the mobile computing device. The textual query is determined to include a carrier phrase of one or more words that is reserved by a first third-party application program installed on the computing device. The first third-party application is selected, from a group of one or more third-party applications, to receive all or a part of the textual query. All or a part of the textual query is provided to the selected first application program.

Abstract: Techniques for fine-tuning language models using target language vocabulary and parallel data for machine translation are disclosed. In an example method, a computing device receives one or more words in a source language. The computing device translates the one or more words to a target language using a fine-tuned language model. The language model is fine-tuned by accessing a foundation language model pre-trained using source language training data and having a source language vocabulary. A set of tokens is added to the model representing a target language vocabulary. The model is further trained using target language training data. The model is further trained using parallel training data including a number of parallel elements each parallel element including words in the source language and the corresponding words in the target language. The computing device outputs the translated one or more words in the target language.

Abstract: Methods and systems for using voice (e.g., voice commands) to control a plurality of network devices via a motion sensing control device are provided. A control device can detect movement (e.g., a gesture) associated with the control device. Based on the movement satisfying a predefined condition, the control device can initiate a either a direct or a proxy communication session with a remote computing device. The communication session can be established and maintained for a predefined period such that data associated with a command can be immediately transmitted to the remote computing device. Thus, when a voice command is received, data associated with the command can be transmitted over the already established communication session to the remote computing device. The remote computing device can provide a response to the control device and/or transmit a command code associated with the voice command to one or more devices intended to be controlled.

Abstract: A speech-processing system may provide access to multiple virtual assistants via a user device. A user may invoke a particular virtual assistant by speaking its wakeword. The virtual assistants may send notifications to the user via the user device, which may present an indication of the available notifications. The user may request delivery of the notifications using, for example, a voice user interface. When delivering notifications from multiple virtual assistants, the system may use distinct voice and/or visual characteristics to indicate a source of the notifications. For example, after delivering a first notification corresponding to a first virtual assistant (e.g., the one invoked by the user at the beginning of the interaction) the first virtual assistant may offer to deliver a second notification from a second virtual assistant. The second virtual assistant may deliver the second notification using voice/visual characteristics different from those used for the first notification.

Abstract: Systems and methods for audio processing include capturing first sound data via at least one microphone of a network microphone device (NMD) and determining, via a voice activity detection process, that the first sound data does not include voice activity. The first sound data is stored in a buffer, and the NMD forgoes spatial processing of the first sound data. The NMD can capture second sound data and determine, via the voice activity process, that the second sound data includes voice activity. The NMD spatially processes the second sound data to produce filtered sound data. The NMD detects a wake word based on data in the buffer. After detecting the wake word, the NMD may determine an action to be performed based on the data in the buffer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sanitizing artificial intelligence prompts. One of the methods includes receiving a message a) for an external system and b) that comprises two or more phrases; for at least one phrase from the two or more phrases: determining a context of the phrase in the message; determining, using the context, whether modification of the phrase will likely maintain an intent of the message; determining whether to permit unedited transmission of the message to the external system using a result of at least one of one or more determinations whether modification of the phrase will likely maintain the intent of the message; and performing one or more actions using a result of the determination whether to permit unedited transmission of the message to the external system.

Abstract: A method and apparatus for encoding/decoding audio signal are provided. The encoding method includes transforming an input audio signal in a time domain into an audio signal in a frequency domain, quantizing energy of a frequency band of the audio signal in the frequency domain, generating a normal signal by normalizing the audio signal in the frequency domain according to quantized energy, obtaining a feature vector including information on the energy of the frequency band based on the normal signal and the input audio signal, quantizing the feature vector, obtaining a scale factor used to scale the normal signal based on the quantized feature vector, quantizing an adjustment signal into which the normal signal has been scaled based on the scale factor, and outputting bitstreams based on the quantized energy, the quantized feature vector, and the quantized adjustment signal.

Abstract: A method performed by an encoder. The method comprises determining envelope representation residual coefficients as first compressed envelope representation coefficients subtracted from the input envelope representation coefficients. The method comprises transforming the envelope representation residual coefficients into a warped domain so as to obtain transformed envelope representation residual coefficients. The method comprises applying, at least one of a plurality of gain-shape coding schemes on the transformed envelope representation residual coefficients in order to achieve gain-shape coded envelope representation residual coefficients, where the plurality of gain-shape coding schemes have mutually different trade-offs in one or more of gain resolution and shape resolution for one or more of the transformed envelope representation residual coefficients.

Abstract: The input of a user is monitored and a location of the user and a language of the user are detected. The input is converted to a text string in the detected user language and the converted text string is parsed into parsed tokens. A command line and correlated parameters indicated by the input are recognized based on the parsed tokens. The recognized command line with the assigned parameters is executed.