-
公开(公告)号：US11646018B2
公开(公告)日：2023-05-09
申请号：US16829705
申请日：2020-03-25
发明人： Vinay Maddali , David Looney , Kailash Patil
IPC分类号： G10L15/197 , G10L15/18 , G10L15/02 , G10L15/04 , G10L15/06 , G10L15/22 , G10L25/84 , G10L25/21 , H04M3/51
CPC分类号： G10L15/197 , G10L15/02 , G10L15/04 , G10L15/063 , G10L15/1822 , G10L15/22 , G10L25/21 , G10L25/84 , H04M3/5183 , H04M2203/558
摘要： Embodiments described herein provide for automatically classifying the types of devices that place calls to a call center. A call center system can detect whether an incoming call originated from voice assistant device using trained classification models received from a call analysis service. Embodiments described herein provide for methods and systems in which a computer executes machine learning algorithms that programmatically train (or otherwise generate) global or tailored classification models based on the various types of features of an audio signal and call data. A classification model is deployed to one or more call centers, where the model is used by call center computers executing classification processes for determining whether incoming telephone calls originated from a voice assistant device, such as Amazon Alexa® and Google Home®, or another type of device (e.g., cellular/mobile phone, landline phone, VoIP).
-
公开(公告)号：US11632460B2
公开(公告)日：2023-04-18
申请号：US17201849
申请日：2021-03-15
发明人： Ricardo Casal , Theo Walker , Kailash Patil , John Cornwell
摘要： Embodiments described herein provide for performing a risk assessment using graph-derived features of a user interaction. A computer receives interaction information and infers information from the interaction based on information provided to the computer by a communication channel used in transmitting the interaction information. The computer may determine a claimed identity of the user associated with the user interaction. The computer may extract features from the inferred identity and claimed identity. The computer generates a graph representing the structural relationship between the communication channels and claimed identities associated with the inferred identity and claimed identity. The computer may extract additional features from the inferred identity and claimed identity using the graph. The computer may apply the features to a machine learning model to generate a risk score indicating the probability of a fraudulent interaction associated with the user interaction.
-
公开(公告)号：US11335353B2
公开(公告)日：2022-05-17
申请号：US16889337
申请日：2020-06-01
发明人： Elie Khoury , Matthew Garland
IPC分类号： G10L17/26 , H04L29/06 , G06F21/32 , G06K9/62 , G10L25/30 , G10L17/18 , G10L17/04 , G10L15/26 , G06V40/10 , G06V40/16 , G06V40/50
摘要： A score indicating a likelihood that a first subject is the same as a second subject may be calibrated to compensate for aging of the first subject between samples of age-sensitive biometric characteristics. Age of the first subject obtained at a first sample time and age of the second subject obtained at a second sample time may be averaged, and an age approximation may be generated based on at least the age average and an interval between the first and second samples. The age approximation, the interval between the first and second sample times, and an obtained gender of the subject are used to calibrate the likelihood score.
-
公开(公告)号：US20220084509A1
公开(公告)日：2022-03-17
申请号：US17475226
申请日：2021-09-14
发明人： Ganesh SIVARAMAN , Avrosh KUMAR , Elie KHOURY
摘要： Embodiments described herein provide for a machine-learning architecture system that enhances the speech audio of a user-defined target speaker by suppressing interfering speakers, as well as background noise and reverberations. The machine-learning architecture includes a speech separation engine for separating the speech signal of a target speaker from a mixture of multiple speakers' speech, and a noise suppression engine for suppressing various types of noise in the input audio signal. The speaker-specific speech enhancement architecture performs speaker mixture separation and background noise suppression to enhance the perceptual quality of the speech audio. The output of the machine-learning architecture is an enhanced audio signal improving the voice quality of a target speaker on a single-channel audio input containing a mixture of speaker speech signals and various types of noise.
-
公开(公告)号：US20210266403A1
公开(公告)日：2021-08-26
申请号：US17317575
申请日：2021-05-11
发明人： Akanksha , Terry NELMS, II , Kailash PATIL , Chirag TAILOR , Khaled LAKHDHAR
摘要： Embodiments described herein provide for detecting whether an Automatic Number Identification (ANI) associated with an incoming call is a gateway, according to rules-based models and machine learning models generated by the computer using call data stored in one or more databases.
-
公开(公告)号：US20210241776A1
公开(公告)日：2021-08-05
申请号：US17165180
申请日：2021-02-02
发明人： Ganesh SIVARAMAN , Elie KHOURY , Avrosh KUMAR
摘要： Embodiments described herein provide for systems and methods for voice-based cross-channel enrollment and authentication. The systems control for and mitigate against variations in audio signals received across any number of communications channels by training and employing a neural network architecture comprising a speaker verification neural network and a bandwidth expansion neural network. The bandwidth expansion neural network is trained on narrowband audio signals to produce and generate estimated wideband audio signals corresponding to the narrowband audio signals. These estimated wideband audio signals may be fed into one or more downstream applications, such as the speaker verification neural network or embedding extraction neural network. The speaker verification neural network can then compare and score inbound embeddings for a current call against enrolled embeddings, regardless of the channel used to receive the inbound signal or enrollment signal.
-
公开(公告)号：US20210240837A1
公开(公告)日：2021-08-05
申请号：US17159748
申请日：2021-01-27
发明人： Hung Wei TSENG , Kailash PATIL
摘要： Embodiments described herein provide for performing a risk assessment. A computer identifies and stores heterogeneous events between a user and a provider system in which the user interacts with an account. The computer may store the heterogeneous events in a table. The stored event information normalizes the events associated with an account. The computer may determine static risk contributions associated with the event information of the account and store the static risk contributions in the table. The computer groups the static risk contributions into predetermined groups. The static risk contributions in each group are converted into dynamic risk contributions. The dynamic risk contributions of each group are aggregated, and the aggregate value of the dynamic risk contributions are fed to a machine learning model. The machine learning model determines a risk score associated with the account.
-
公开(公告)号：US20210152897A1
公开(公告)日：2021-05-20
申请号：US17157848
申请日：2021-01-25
发明人： Nick GAUBITCH , Scott STRONG , John CORNWELL , Hassan KINGRAVI , David DEWEY
摘要： Systems, methods, and computer-readable media for call classification and for training a model for call classification, an example method comprising: receiving DTMF information from a plurality of calls; determining, for each of the calls, a feature vector including statistics based on DTMF information such as DTMF residual signal comprising channel noise and additive noise; training a model for classification; comparing a new call feature vector to the model; predicting a device type and geographic location based on the comparison of the new call feature vector to the model; classifying the call as spoofed or genuine; and authenticating a call or altering an IVR call flow.
-
公开(公告)号：US20210134316A1
公开(公告)日：2021-05-06
申请号：US17121291
申请日：2020-12-14
发明人： Elie KHOURY , Matthew GARLAND
摘要： Methods, systems, and apparatuses for audio event detection, where the determination of a type of sound data is made at the cluster level rather than at the frame level. The techniques provided are thus more robust to the local behavior of features of an audio signal or audio recording. The audio event detection is performed by using Gaussian mixture models (GMMs) to classify each cluster or by extracting an i-vector from each cluster. Each cluster may be classified based on an i-vector classification using a support vector machine or probabilistic linear discriminant analysis. The audio event detection significantly reduces potential smoothing error and avoids any dependency on accurate window-size tuning. Segmentation may be performed using a generalized likelihood ratio and a Bayesian information criterion, and the segments may be clustered using hierarchical agglomerative clustering. Audio frames may be clustered using K-means and GMMs.
-
公开(公告)号：US10692502B2
公开(公告)日：2020-06-23
申请号：US15910387
申请日：2018-03-02
发明人： Elie Khoury , Parav Nagarsheth , Kailash Patil , Matthew Garland
摘要： An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.
-
-
-
-
-
-
-
-
-
搜索结果
142 条记录 (耗时 0.026 秒)
