565 results about "Confidence threshold" patented technology

A speech processing system that performs adaptations based upon non-sound external input, such as weather input. In the system, an acoustic environment can include a microphone and speaker. The microphone/speaker can receive/produce speech input/output to/from a speech processing system. An external input processor can receive non-sound input relating to the acoustic environment and to match the received input to a related profile. A setting adjustor can automatically adjust settings of the speech processing system based upon a profile based upon input processed by the external input processor. For example, the settings can include customized noise filtering algorithms, recognition confidence thresholds, output energy levels, and/or transducer gain settings.

The invention discloses an initiative study-based questioning and answering method and a questioning and answering system adopting the initiative study-based questioning and answering method, wherein the Initiative study-based questioning and answering method comprises the following steps of (1) performing question inputting; (2) performing pretreatment; (3) performing feature extraction; (4) performing question understanding; (5) performing judgment of confidence, a threshold value and credibility; (6) performing information retrieval and information processing; (7) performing answer extraction; (8) performing initiative study; (9) performing guide questioning according to the specific type of the question when the confidence is lower than the credibility, initiatively guiding a user to question without ambiguity and performing a new round of more effective questioning and answering. The questioning and answering system comprises five modules including a question inputting module, a pretreatment module, a semantics understanding module, an initiative study module and an answer outputting module.

Disclosed is a system and method for suggesting messages that are automatically learned, personalized and diversified by leveraging messages sent by a large number of users in order to provide message completions that are as engaging as possible. The disclosed systems and methods learn from recurrent messages sent to a recipient, and suggest message completions based upon user behavior. The systems and methods compute a ranked list of suggested message completions after every key stroke or character input, and if the list satisfies a given confidence threshold, it is returned and displayed to the user.

A method of configuring a speech recognition unit in a vehicle. The method includes receiving a noise error from the speech recognition unit responsive to a user voice command and reducing a confidence threshold for an appropriate grammar set responsive to the received noise error.

The invention discloses a method for the mixed customer services of intelligent robots and human beings. The method comprises the steps of S1, receiving the user information sent by a user terminal; S2, searching a database through triggering an intelligent robot based on the user information to obtain a search result; S3, judging whether the search result is correct or not based on an answer candidate method; on the condition that the search result is correct, returning the search result to the user terminal and getting back to the step S1; on the condition that the search result is not correct, triggering the human being-based service; giving a reply to a question based on the user information by the human being-based service and marking the replay as an effective answer; S4, recording the user information and the effective answer corresponding to the user information into the database by the intelligent robot. According to the technical scheme of the invention, questions are answered by the intelligent robot as much as possible. Meanwhile, based on a confident threshold, whether a question is forwarded to the human being-based service or not is intelligently judged. After the question is answered by the human being-based service, the intelligent robot automatically records the question and the answer into the database. Therefore, the self-learning of the intelligent robot database and the knowledge timely update are realized.

Systems and methods are provided for validating the authenticity of a signature on a document by providing a document from an account, the document including an actual signature and a machine-readable identifier, wherein the machine-readable identifier contains a string of data representing the integral characteristics of all valid account signatures and a person-specific confidence threshold. When the document is presented at a point of presentment, the document is scanned into a document-processing machine and the actual signature is compared against all valid account signatures.

A method for quickly identifying lanes-change condition of object vehicle includes utilizing machine vision and radar to collect horizontal and longitudinal distances, relative speed and the same lane possibility between object vehicle and local vehicle, making comparison and quantization on said data collected each time, making compensation and tracking prediction on relevant data, calculating confidence of each vehicle by using two layers of neural network training to obtain object vehicle weight and setting object vehicle to be dangerous object once calculated confidence coefficient is over confidence threshold.

The present invention provides a neural network-based face detection model training method, a neural network-based face detection method, a neural network-based face detection model training system and a neural network-based face detection system. The training method includes the following steps that: the loss function of the bias network layer of a prediction face frame is calculated according to the bias information of the prediction face frame relative to a default face frame and the bias information of a real face frame relative to the default face frame; the loss function of the confidence network layer of the prediction face frame is calculated according to the confidence of the default face frame; the error of the two loss functions is calculated, and is fed back to a neural network, so that the weight of the neural network is adjusted; iterative training is repeated until convergence appears, so that a face detection model can be obtained, and therefore, the prediction face frame can contain a face more accurately. The detection method includes the following steps that: a face image to be detected is inputted to a trained face detection model, bias information and confidence are outputted; corresponding prediction face frames are calculated according to the bias information; and a prediction face frame corresponding to confidence greater than a preset confidence threshold or the highest confidence is selected as a face detection result.

This invention is an ultra-low frequency electromagnetic telemetry receiver which fuses multiple input receive sources to synthesize a decodable message packet from a noise corrupted telemetry message string. Each block of telemetry data to be sent to the surface receiver from a borehole tool is digitally encoded into a data packet prior to transmission. The data packet is modulated onto the ULF EM carrier wave and transmitted from the borehole to the surface and then are simultaneously detected by multiple receive sensors disbursed within the rig environment. The receive sensors include, but are not limited to, electric field and magnetic field sensors. The spacing of the surface receive elements is such that noise generators are unequally coupled to each receive element due to proximity and/or noise generator type (i.e. electric or magnetic field generators). The receiver utilizes a suite of decision metrics to reconstruct the original, non noise-corrupted data packet from the observation matrix via the estimation of individual data frames. The receiver will continue this estimation process until: 1) the message validates, or 2) a preset “confidence threshold” is reached whereby frames within the observation matrix are no longer “trusted”.

An interactive response system mixes HSR subsystems with ASR subsystems to facilitate overall capability of voice user interfaces. The system permits imperfect ASR subsystems to nonetheless relieve burden on HSR subsystems. An ASR proxy is used to implement an IVR system, and the proxy dynamically determines how many ASR and HSR subsystems are to perform recognition for any particular utterance, based on factors such as confidence thresholds of the ASRs and availability of human resources for HSRs.

A system for processing images captured in a retail store is provided. The system may include a processor configured to: access a database storing a group of product models; receive an image depicting at least part of a store shelf having a plurality of products of a same type displayed thereon; analyze the image and determine a first candidate type of the products based on the group of product models and the image analysis; determine a first confidence level associated with the first candidate type; when the first confidence level is below a confidence threshold, determine a second candidate type of the products using contextual information; determine a second confidence level associated with the determined second candidate type of the plurality of products; and when the second confidence level is above the confidence threshold, initiate an action to update the group of product models stored in the database.

A method and system for training a special object detector to distinguish a foreground object appearing in a sequence of frames for a target domain. The sequence of frames depicts motion of the foreground object in a non-uniform background. The foreground object is detected in a high-confidence subwindow of an initial frame of the sequence, which includes computing a measure of confidence that the high-confidence subwindow includes the foreground object and determining that the measure of confidence exceeds a specified confidence threshold. The foreground object is tracked in respective positive subwindows of subsequent frames appearing after the initial frame. The subsequent frames are within a specified short period of time. The positive subwindows are used to train the special object detector to detect the foreground object in the target domain. The positive subwindows include the subwindow of the initial frame and the respective subwindows of the subsequent frames.

A method is provided of a bank processing a check in an automatic signature verification system. The method comprises receiving a check image having a payor's signature, extracting the payor's signature from the check image, comparing the extracted payor's signature with a reference signature, providing a confidence value based upon the comparison of the extracted payor's signature with the reference signature, selecting one of a plurality of confidence threshold values based upon amount of the check, and comparing the confidence value with the selected confidence threshold value to determine if payment of the check amount is approved.

Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.