Abstract: This application discloses an intent recognition optimization processing method, apparatus, device and storage medium, and relates to the field of internet technology. The implementation scheme of specific method includes: acquiring a first intent set and at least one original corpus; acquiring a first recognition result of each original corpus, where the first recognition result of any one of the original corpus includes a first intent corresponding to the original corpus recognized by the intent recognition model; acquiring a second recognition result of each original corpus, where the second recognition result of any one of the original corpus includes a second intent corresponding to the original corpus obtained through artificial recognition; and performing optimization processing on the first intent set to obtain a second intent set according to the first recognition result and the second recognition result of each original corpus.

Abstract: A method and a decoder device of generating a concealment audio subframe of an audio signal are provided. The method comprises generating frequency spectra on a subframe basis where consecutive subframes of the audio signal have a property that an applied window shape of first subframe of the consecutive subframes is a mirrored version or a time reversed version of a second subframe of the consecutive subframes. Peaks of a signal spectrum of a previously received audio signal are detected for a concealment subframe, and a phase of each of the peaks is estimated. A time reversed phase adjustment is derived based on the estimated phase and applied to the peaks of the signal spectrum to form time reversed phase adjusted peaks.

Abstract: The present disclosure describes systems and methods for extensible search, content, and dialog management. Embodiments of the present disclosure provide a dialog system with a trained intent recognition model (e.g., a deep learning model) to receive and understand a natural language query from a user. In cases where intent is not identified for a received query, the dialog system generates one or more candidate responses that may be refined (e.g., using human-in-the-loop curation) to generate a response. The intent recognition model may be updated (e.g., retrained) the accordingly. Upon receiving a subsequent query with similar intent, the dialog system may identify the intent using the updated intent recognition model.

Abstract: Systems and methods are disclosed for a voice/chatbot building system. The voice/chatbot builder may involve receiving an identified intent, receiving a task related to the identified intent, and receiving a response related to both the identified intent and the task. The identified intent, task, and response may form a first conversation. The first conversation may be linked to other conversations to establish contextual relationships among conversations and determine conversation priority. Voice/chatbot building may also train natural language processing machine learning algorithms.

Abstract: A computing device translates a spoken word into a corresponding ordered set of spoken phonemes and analyzes correctness of the spoken word relative to a target word. The analyzing includes attempting to locate each of the spoken phonemes in an ordered set of grapheme-phoneme correspondences (GPCs) describing the target word, and determining whether or not the ordered set of spoken phonemes comprises a same number of phonemes as in the ordered set of GPCs. The analyzing also includes comparing the order of the ordered set of spoken phonemes against the order of the ordered set of GPCs. The computing device generates a report, based on the analyzing, that identifies at least one of the GPCs in the ordered set of GPCs as having been incorrectly applied in decoding the target word.

Abstract: A system and method of operating a system for automatically punctuating text using non-recurrent neural networks is disclosed. The system and method at least: applying a text string to a first component of a non-recurrent neural network trained to generate one or more contextualized vectors, wherein the first component determines the contextualized vectors by processing each word in the text string in parallel with one another; applying the contextualized vectors to a second component of the non-recurrent neural network trained to generate a set of probability values for each word in the text string, wherein the second component determines the set of probability values by processing the contextualized vectors in parallel with one another; and transmitting the set of probability values to a text generation engine to generate a formatted text string based on the set of probability values.

Abstract: A scripted audio production system in which the scripted audio production computerized process decreases production time by improving computerized processes and technological systems for pronunciation research and script preparation, narration, editing, proofing and mastering. The system enables the user to upload their manuscript and recorded audio of the narration of the manuscript to the system. The system then compares the recorded audio against previously uploaded manuscript and any mistakes or deviations from the manuscript are highlighted or otherwise indicated to the user. The system automatically pieces together the last-read audio into a clean file without the need for significant user interaction. The process may also be performed on the recorded audio by the narrator first uploading the audio and manuscript to the scripted audio production technology system.

Abstract: Disclosed is a voice activity detection (VAD) device and method capable of referring to an environment detection result and thereby selecting one of multiple VAD results as a basis for determining whether a voice activity occurs. The VAD device includes an environment detection circuit, a VAD circuit, and a voice activity decision circuit. The environment detection circuit is configured to process an audio input signal and thereby generate an environment detection result. The VAD circuit is configured to analyze the audio input signal with multiple VAD algorithms and thereby generate multiple VAD results. The voice activity decision circuit is configured to select one of the multiple VAD results according to the environment detection result.

Abstract: A voice processing method is provided for a terminal. The method includes: performing voice speed detection on a voice obtained from a voice source, to obtain a voice speed value of the voice; obtaining a forward error correction (FEC) redundancy; adjusting the FEC redundancy according to the voice speed value to obtain a target redundancy; performing voice encoding on the voice to obtain a voice encoded packet; performing FEC encoding on the voice encoded packet according to the target redundancy to obtain a redundancy packet; and transmitting the redundancy packet and the voice encoded packet to a receiving end.

Abstract: In various implementations described herein, a partial free-form natural language input may be received from a user at an input component of a computing device. The partial free-form natural language input may identify an entity without identifying a responsive action and may be directed by the user to an automated assistant that operates at least in part on the computing device. The partial free-form natural language input may be analyzed to identify the entity. Based on the identified entity, a plurality or superset of candidate responsive actions may be identified, filtered, and/or ranked based on one or more signals. The automated assistant may then provide output that recommends one or more of the candidate responsive actions based on the ranking and/or filtering.

Abstract: Proposed are a machine translation apparatus and a machine translation method for displaying a translation result through a user interface. The machine translation method may include: display an initial machine translation result for a first translation target sentence; correcting the initial machine translation result according to a manipulation result of a user on the user interface unit, and displaying the corrected machine translation result; and analyzing a difference between the corrected machine translation result and the initial machine translation result, and reflecting the analysis result to perform machine translation on a second translation target sentence. The machine translation apparatus and the method can be used to efficiently acquire a high-quality translation within a short time while minimizing time, cost and effort of a user, which used to be required for a conventional machine translation process.

Abstract: A system is provided to categorize voice prints during a voice authentication. The system includes a processor and a computer readable medium operably coupled thereto, to perform voice authentication operations which include receiving an enrollment of a user in the biometric authentication system, requesting a first voice print comprising a sample of a voice of the user, receiving the first voice print of the user during the enrollment, accessing a plurality of categorizations of the voice prints for the voice authentication, wherein each of the plurality of categorizations comprises a portion of the voice prints based on a plurality of similarity scores of distinct voice prints in the portion to a plurality of other voice prints, determining, using a hidden layer of a neural network, one of the plurality of categorizations for the first voice print, and encoding the first voice print with the one of the plurality of categorizations.

Abstract: Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence comprising a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set and includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence comprising a third set of speech frame feature vectors. The third speech sequence is processed using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors, and using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.

Abstract: A system accesses a first digital audio file that includes a plurality of spoken instructions. The system converts the first digital audio file to a first spectrogram image, applies a filter to determine whether an image quality of the first spectrogram image is below a predetermined image quality, and in response, generates a second spectrogram image from the first spectrogram image using a training model. The system converts the second spectrogram image to a second digital audio file and converts the second digital audio file into multiple vectors that each correspond to a particular spoken instruction. The system identifies related vectors and concatenates the related vectors together in order to create a plurality of concatenated vectors. The system generates, using the plurality of concatenated vectors, a third digital audio file that includes concatenated spoken instructions from the first digital audio file.

Abstract: A computer generates a formal planning domain description. The computer receives a first text-based description of a domain in an AI environment. The domain includes an action and an associated attribute, and the description is written in natural language. The computer receives the first text-based description of the domain and extracts a first set of domain actions and associated action attributes. The computer receives audio-visual elements depicting the domain, generates a second text-based description, and extracts a second set of domain actions and associated action attributes. The computer constructs finite state machines corresponding to the extracted actions and attributes. The computer converts the FSMs into a symbolic model, written in a formal planning language, that describes the domain.