Abstract: A method of zoning a transcription of audio data includes separating the transcription of audio data into a plurality of utterances. A that each word in an utterances is a meaning unit boundary is calculated. The utterance is split into two new utterances at a work with a maximum calculated probability. At least one of the two new utterances that is shorter than a maximum utterance threshold is identified as a meaning unit.

Abstract: A voice/non-voice determination device robust with respect to an acoustic signal in a high-noise environment is provided. The voice/non-voice determination device includes an acoustic scene classification unit including a first model which receives input of an acoustic signal and outputs acoustic scene information which is information regarding a scene where the acoustic signal is collected, a speech enhancement unit including a second model which receives input of the acoustic signal and outputs speech enhancement information which is information regarding the acoustic signal after enhancement, and a voice/non-voice determination unit including a third model which receives input of the acoustic signal, the acoustic scene information and the speech enhancement information and outputs a voice/non-voice label which is information regarding a label of either a speech section or a non-speech section.

Abstract: Disclosed are systems and methods for generating voice renderings of machine-generated electronic messages. The disclosed systems and methods provide a novel framework for organizing often fragmented machine-generated electronic messages and providing mechanisms for a virtual assistant to produce voice-renderings data extracted from electronic messages. The disclosed system may implement steps for receiving user queries via virtual assistants, extracting data from machine-generated electronic messages, converting the extracted data to purposeful organizational schemas, and generating human perceivable voice renderings based on the user queries and extracted data.

Abstract: Embodiments are directed to a companding method and system for reducing coding noise in an audio codec. A method of processing an audio signal includes the following operations. A system receives an audio signal. The system determines that a first frame of the audio signal includes a sparse transient signal. The system determines that a second frame of the audio signal includes a dense transient signal. The system compresses/expands (compands) the audio signal using a companding rule that applies a first companding exponent to the first frame of the audio signal and applies a second companding exponent to the second frame of the audio signal, each companding exponent being used to derive a respective degree of dynamic range compression and expansion for a corresponding frame. The system then provides the companded audio signal to a downstream device.

Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.

Abstract: Techniques for data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes generating a list of values to cover for an entity, selecting utterances from a set of data that have context for the entity, converting the utterances into templates, where each template of the templates comprises a slot that maps to the list of values for the entity, selecting a template from the templates, selecting a value from the list of values based on the mapping between the slot within the selected template and the list of values for the entity; and creating an artificial utterance based on the selected template and the selected value, where the creating the artificial utterance comprises inserting the selected value into the slot of the selected template that maps to the list of values for the entity.

Abstract: Provided is a method, computer program product, and system for fusing knowledge graphs to generate a larger knowledgebase for responding to cross document questions. A processor may extract contextual information from a plurality of documents. The processor may generate, based on the extracted contextual information, a knowledge graph for each document of the plurality of documents. The processor may analyze each knowledge graph to determine if one or more entities of each knowledge graph are linked. The processor may fuse, in response to an entity in a first knowledge graph being linked to an entity in a second knowledge graph, the first knowledge graph with the second knowledge graph to create a fused knowledge graph.

Abstract: A chatbot capable of empathic engagement with a user is disclosed. An identified trend in a user's mood or goals between a first time and a second time can be associated with open input (e.g., open text string input) from the user. As the user's mood or goals continue to be tracked, a subsequent trend can be identified that is the same as, similar to, different from, or opposite to the first identified trend. The user can then be automatically engaged based on the open input associated with the first identified trend. In an example, a user may input thoughts or reasons why they have been having a positively trending mood over a duration of time. The chatbot can then repeat or otherwise use those same thoughts or reasons to engage the user empathically when the chatbot detects that the user is experiencing a negatively trending mood.

Abstract: A sensor device transmits, to an external device installed external to the sensor device, sensing data generated from monitoring a target, and includes a sensor unit that generates sensing data including background noise data. The background noise data represents noise from a cause other than the target. The sensor device further includes an extraction unit that extracts the background noise data from the sensing data, and a transmission unit that transmits the background noise data extracted by the extraction unit to the external device.

Abstract: This disclosure relates generally to retrieval of prior court cases using witness testimonies. Conventional state-of-the-art methods use supervised techniques for answering basic questions in legal domain using numerous features and do not address interpretability of results and the performance and precision of retrieving prior court cases for these methods are less. Embodiments of the present disclosure obtains an embedded representation for an event structure of a user query and testimony sentences identified from prior court cases using a trained Bi-LSTM classifier and a set of linguistic rules. A similarity is estimated between the embedded representation for the event structure of the user query and the event structure of each testimony sentence from the prior court cases. Further a relevance score is assigned in accordance with the estimated similarity to retrieve the relevant prior court cases. The disclosed method is used to retrieve the relevant prior court cases using witness testimonies.

Abstract: Methods, systems, apparatuses, and computer program products are provided for extracting an entity value from a sentence. An embedding set that may include one or more sentence embeddings is generated for at least part of a first sentence that is tagged to associate a first named entity in the sentence with an entity type. A plurality of candidate embeddings is also generated for at least part of a second sentence. The one or more sentence embeddings in the embedding set may be compared with each of the plurality of candidate embeddings, and a match score may be assigned to each comparison to generate a match score set. A particular match score of the match score set may be identified that exceeds a similarity threshold, and an entity value of the entity type may be extracted from the second sentence associated with the identified match score.

Abstract: Systems and methods that offer significant improvements to current chatbot conversational experiences are disclosed. The proposed systems and methods are configured to manage conversations in real-time with human customers based on a dynamic and unscripted conversation flow with a virtual assistant. In one embodiment, a knowledge graph or domain model represents the sole or primary source of information for the virtual assistant, thereby removing the reliance on any form of conversational modelling. Based on the information provided by the knowledge graph, the virtual agent chatbot will be equipped to answer customer queries, as well as demonstrate reasoning, offering customers a more natural and efficacious dialogue experience.

Abstract: A speech synthesizer for evaluating quality of a synthesized speech using artificial intelligence includes a database configured to store a synthesized speech corresponding to text, a correct speech corresponding to the text and a speech quality evaluation model for evaluating the quality of the synthesized speech, and a processor configured to compare a first speech feature set indicating a feature of the synthesized speech and a second speech feature set indicating a feature of the correct speech, acquire a quality evaluation index set including indices used to evaluate the quality of the synthesized speech according to a result of comparison, and determine weights as model parameters of the speech quality evaluation model using the acquired quality evaluation index set and the speech quality evaluation model.

Abstract: A computer device (100) for processing audio signals is described. The computer device (100) includes at least a processor and a memory. The computer device (100) is configured to receive a bitstream comprising a combined audio signal, the combined audio signal comprising a first audio signal including speech and a second audio signal. The computer device (100) is configured to compress the combined audio signal to provide a compressed audio signal. The computer device (100) is configured to control a dynamic range of the compressed audio signal to provide an output audio signal. In this way, a quality of the speech included in the output audio signal is improved.

Abstract: A method, computer program product, and computing system for obtaining calibration information for a three-dimensional space incorporating an ACI system; and processing the calibration information to calibrate the ACI system.

Abstract: The present invention relates to method and device for text-enhanced knowledge graph joint representation learning, the method at least comprises: learning a structure vector representation based on entity objects and their relation linking in a knowledge graph and forming structure representation vectors; discriminating credibility of reliable feature information and building an attention mechanism model, aggregating vectors of different sentences and obtain association-discriminated text representation vectors; and building a joint representation learning model, and using a dynamic parameter-generating strategy to perform joint learning for the text representation vectors and the structure representation vectors based on the joint representation learning model. The present invention selective enhances entity/relation vectors based on significance of associated texts, so as to provide improved semantic expressiveness, and uses 2D convolution operations to train joint representation vectors.

Abstract: A method of sampling output audio samples includes, during a packet loss concealment event, obtaining a sequence of previous output audio samples. At each time step during the event, the method includes generating a probability distribution over possible output audio samples for the time step. Each sample includes a respective probability indicating a likelihood that the corresponding sample represents a portion of an utterance at the time step. The method also includes determining a temperature sampling value based on a function of a number of time steps that precedes the time step, and an initial, a minimum, and a maximum temperature sampling value. The method also includes applying the temperature sampling value to the probability distribution to adjust a probability of selecting possible samples and randomly selecting one of the possible samples based on the adjusted probability. The method also includes generating synthesized speech using the randomly selected sample.

Abstract: In accordance with embodiments of the present disclosure, a method for processing audio information in an audio device may include reproducing audio information by generating an audio output signal for communication to at least one transducer of the audio device, receiving at least one input signal indicative of ambient sound external to the audio device, detecting from the at least one input signal a near-field sound in the ambient sound, and modifying a characteristic of the audio information reproduced to the at least one transducer in response to detection of the near-field sound.

Abstract: Determining slot value(s) based on received natural language input and based on descriptor(s) for the slot(s). In some implementations, natural language input is received as part of human-to-automated assistant dialog. A natural language input embedding is generated based on token(s) of the natural language input. Further, descriptor embedding(s) are generated (or received), where each of the descriptor embeddings is generated based on descriptor(s) for a corresponding slot that is assigned to a domain indicated by the dialog. The natural language input embedding and the descriptor embedding(s) are applied to layer(s) of a neural network model to determine, for each of the slot(s), which token(s) of the natural language input correspond to the slot. A command is generated that includes slot value(s) for slot(s), where the slot value(s) for one or more of slot(s) are determined based on the token(s) determined to correspond to the slot(s).

Abstract: Provided are a voice synthesis method, an apparatus, a device, and a storage medium, involving obtaining text information and determining characters in the text information and a text content of each of the characters; performing a character recognition on the text content of each of the characters, to determine character attribute information of each of the characters; obtaining speakers in one-to-one correspondence with the characters according to the character attribute information of each of the characters, where the speakers are pre-stored pronunciation object having the character attribute information; and generating multi-character synthesized voices according to the text information and the speakers corresponding to the characters of the text information. These improve pronunciation diversities of different characters in the synthesized voices, improve an audience's discrimination between different characters in the synthesized voices, and thereby improve experience of a user.