-
公开(公告)号：US11645460B2
公开(公告)日：2023-05-09
申请号：US17135283
申请日：2020-12-28
发明人： Avraham Faizakof , Arnon Mazza , Lev Haikin , Eyal Orbach
IPC分类号： G06F40/232 , G06N20/00 , G06F40/279 , G06F40/169 , G10L15/04 , G10L15/06 , G10L15/197 , G10L15/22
CPC分类号： G06F40/232 , G06F40/169 , G06F40/279 , G06N20/00 , G10L15/04 , G10L15/063 , G10L15/197 , G10L15/22
摘要： A first text corpus comprising punctuated and capitalized text is received. The words in the first text corpus are then annotated with a set of labels indicating a punctuation and a capitalization of each word. At an initial training stage, a machine learning model is trained on a first training set using the annotated words from the first text corpus and the labels. A second text corpus is received representing conversational speech. The words in the second text corpus are then annotated with the set of labels. In a re-training stage, the machine learning model is re-trained on a second training set comprising the annotated words from the second text corpus, and the labels. At an inference stage, the trained machine learning model is applied to a target set of words representing conversational speech to predict a punctuation and capitalization of each word in the target set.
-
公开(公告)号：US11574642B2
公开(公告)日：2023-02-07
申请号：US16915160
申请日：2020-06-29
IPC分类号： G10L19/005 , G10L15/08 , G10L15/14 , G10L15/20 , G10L19/00 , G10L15/02 , G10L25/18 , G10L25/21
摘要： A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.
-
公开(公告)号：US11494057B2
公开(公告)日：2022-11-08
申请号：US16924881
申请日：2020-07-09
发明人： Christopher Carl Highman , Kyle Duke , Guysung Kim , Armando Luja , Michael J. Weldy , Kevin Wiegand
IPC分类号： G06F9/54 , G06F9/50 , H04L29/08 , G06F3/0484 , G06F9/451 , G06F40/14 , G06F9/455 , G06Q30/00 , H04L41/12 , G06F21/62 , H04L67/1097 , H04L67/02 , H04L41/0859 , H04L41/5041 , H04L41/0869 , G06F21/57 , H04L41/50 , H04L41/0233
摘要： A system and method are presented for delivering modular tools through a cloud-based remote computing environment. Users may create and customize extensions to the modular tools for integration with the product system without requiring change to product. Using a script tag added to a website, a user is able to install the modular tool to a website. The modular tool extensions are able to directly communicate with handlers and websites and are able to become directly integrated with a premises-based product. This may be done through a multiplexed API exposed to the modular tool extensions that directly couples them to the premises-based product. The modular tools are able to be configured in the premises-based product, however they are hosted in the cloud and as such, the premises-based product is able to receive continuous integration and deployment from the cloud.
-
公开(公告)号：US11468897B2
公开(公告)日：2022-10-11
申请号：US16910717
申请日：2020-06-24
摘要： A method for selectively transcribing voice communications that includes: receiving keywords; receiving an audio stream of audio data of speech; searching the audio stream to detect keywords or keyword detections and recording parameter data for each that includes a location of the keyword within the audio stream; generating one or more cumulative datasets for one or more portions of the audio stream that each includes parameter data for the keyword detections occurring therein; for each of the one or more portions of the audio stream, calculating a transcription favorableness score via inputting the corresponding one of the one or more cumulative datasets into an algorithm; and determining whether to transcribe each of the one or more portions of the audio stream by comparing the corresponding transcription favorableness score against a predetermined threshold.
-
5.发明申请公开(公告)号：US20220182493A1
公开(公告)日：2022-06-09
申请号：US17545191
申请日：2021-12-08
发明人： Wei Xun Ter , Geir Rosoy , Mohamed Shahul Hameed , Bayu Wicaksono , Travis Humphreys , Brian Robinson
摘要： A system for estimating a wait time to connect a customer to an agent according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to receive incoming interaction data from the customer indicative of a request to estimate the wait time, retrieve historical data indicative of interaction information for one or more interactions that have already been serviced in response to receipt of the request, and generate a wait time estimation based on the historical data.
-
公开(公告)号：US11301908B2
公开(公告)日：2022-04-12
申请号：US16864188
申请日：2020-05-01
发明人： Mohamed Uvaiz Anwar Batcha , Prasanth Balaraman , Asmitha Durairaj , Praveen Kumar Anandadoss , Rajeshkumar Subramanian , Tony Thazhekkaden , Kesavan Ganesan
摘要： A system and method are presented for providing a contextual summary of an interaction between a first party and a second party over a media channel in an interaction transfer to a third party. A request is received to transfer an interaction to the third party, the request being triggered from the interaction. A text transcript of the interaction is obtained. The text transcript is processed to obtain the contextual summary and metadata, which is provided to the third party for handling the interaction with the interaction transfer. The contextual summary is provided by a contextual summarizer, which comprises a custom plurality of application programming interfaces (APIs). The plurality of APIs comprises at least one of: a text summarizer API, a churn predictor API, a sentiment analysis API, a next best action API, and an interaction reference detector API.
-
公开(公告)号：US11301160B2
公开(公告)日：2022-04-12
申请号：US16446092
申请日：2019-06-19
发明人： Vitaly Y. Barinov
摘要： A system and method are presented for a replication protocol in a real-time statistical engine. A real-time statistical engine monitors external data sources and uses received data to derive on-demand statistics. The engine may be comprised of a plurality of instances. In an embodiment with two instances of the engine, the instances are labeled as a primary instance and a backup instance. In case of primary instance failure, client servers of the engine are able to connect to the backup instance and obtain the same statistics with minimal data loss. The communication system between the primary instance and the backup instance may be used to exchange information about requested statistics, to clean unused statistics and to unconditionally delete statistics for which computation has become impossible.
-
公开(公告)号：US11294955B2
公开(公告)日：2022-04-05
申请号：US16378452
申请日：2019-04-08
IPC分类号： G06F16/683 , G10L25/51
摘要： A system and method are presented for optimization of audio fingerprint search. In an embodiment, the audio fingerprints are organized into a recursive tree with different branches containing fingerprint sets that are dissimilar to each other. The tree is constructed using a clustering algorithm based on a similarity measure. The similarity measure may comprise a Hamming distance for a binary fingerprint or a Euclidean distance for continuous valued fingerprints. In another embodiment, each fingerprint is stored at a plurality of resolutions and clustering is performed hierarchically. The recognition of an incoming fingerprint begins from the root of the tree and proceeds down its branches until a match or mismatch is declared. In yet another embodiment, a fingerprint definition is generalized to include more detailed audio information than in the previous definition.
-
公开(公告)号：US11290594B2
公开(公告)日：2022-03-29
申请号：US17363647
申请日：2021-06-30
摘要： A contact center system for performing call progress analysis including tone and speech classification according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the contact center system to determine a cumulative average of an entropy of an audio signal received by the contact center system, determine a cumulative average power spectral amplitude and a cumulative average spectral entropy of the audio signal, calculate a difference measure of the audio signal as a difference between the cumulative average of the entropy and the cumulative average spectral entropy, distinguish tones from speech of the audio signal based on the difference measure, and process one or more tones of the audio signal in response to identification of the one or more tones in the audio signal.
-
公开(公告)号：US20220092686A1
公开(公告)日：2022-03-24
申请号：US17029869
申请日：2020-09-23
发明人： Archana Sekar , Javier Villalobos , Yochai Konig
摘要： A method for data bidding in an enterprise system comprising a first enterprise and a second enterprise using a permissioned blockchain infrastructure according to one embodiment includes receiving, by an end user device, a request for data from an end user; generating, by the end user device, an announcement including the request for data to the enterprise system, wherein the announcement initiates the data bidding by the enterprise system; receiving, by the end user device, at least one bid including requested data of at least one of the first enterprise and the second enterprise in response to the announcement; analyzing, by the end user device, the at least one bid from the at least one of the first enterprise and the second enterprise; selecting, by the end user device, the at least one of the first enterprise and the second enterprise; displaying, by the end user device, the at least one of the first enterprise and the second enterprise to the end user; receiving, by the end user device, an indication that the end user has selected the first enterprise; and transmitting, by the first enterprise, the requested data to the end user thereby completing a data transaction.
-
-
-
-
-
-
-
-
-
搜索结果
661 条记录 (耗时 0.038 秒)
