公开(公告)号：US20210353218A1

公开(公告)日：2021-11-18

申请号：US17322047

申请日：2021-05-17

申请人： Insurance Services Office, Inc.

发明人： Erik Edwards ,  Charles Dognin ,  Bajibabu Bollepalli ,  Maneesh Kumar Singh

IPC分类号： A61B5/00 ,  G10L15/02 ,  G10L25/66 ,  G10L15/14 ,  G10L15/22 ,  G16H50/20

摘要： Machine learning systems and methods for multiscale Alzheimer's dementia recognition through spontaneous speech are provided. The system retrieves one or more audio samples and processes the one or more audio samples to extract acoustic features from audio samples. The system further processes the one or more audio samples to extract linguistic features from the audio samples. Machine learning is performed on the extracted acoustic and linguistic features, and the system indicates a likelihood of Alzheimer's disease based on output of machine learning performed on the extracted acoustic and linguistic features.

公开(公告)号：US20210343277A1

公开(公告)日：2021-11-04

申请号：US17160278

申请日：2021-01-27

申请人： Samsung Electronics Co., Ltd.

发明人： Suhel Jaber ,  Anil Yadav ,  Melvin Lobo ,  Sukrat Gupta

IPC分类号： G10L15/14 ,  G10L25/27

摘要： An electronic device includes an audio sensor, a memory, and at least one processor coupled to the audio sensor and the memory. The at least one processor is configured to receive, via the audio sensor an audio input. The at least one processor is further configured to perform, using an automatic speech recognition (ASR) model and an entity prediction model, out-of-vocabulary prediction of an entity. The at least one processor is further configured to receive an ASR hypothesis including the predicted entity. The at least one processor is further configured to output text including the predicted entity.

公开(公告)号：US11164565B2

公开(公告)日：2021-11-02

申请号：US16561651

申请日：2019-09-05

申请人： LG ELECTRONICS INC.

发明人： Jeehye Lee

IPC分类号： G10L15/14 ,  G06N20/00 ,  G10L15/16 ,  G10L15/01

摘要： A learning system and method for updating recognition performance by assigning weights according to a confidence level of data are discussed. The unsupervised learning system includes a memory configured to store speech data received from a server that performs speech recognition; and a processor configured to measure confidence levels of pieces of learnable data stored in the memory and classify the pieces of learnable data into learning data and adaptation data, generate a learning model by performing unsupervised learning on the learning data, generate an adaption model using the adaptation data, and evaluate speech recognition performance for the learning model and the adaptation model, wherein the processor is configured to assign weights by applying the measured confidence levels to the learning model and the adaptation model and update recognition performance with the learning model and the adaptation model to which the weights are applied.

公开(公告)号：US20210335354A1

公开(公告)日：2021-10-28

申请号：US16487368

申请日：2019-04-19

申请人： LG ELECTRONICS INC.

发明人： Jisoo PARK

IPC分类号： G10L15/22 ,  G10L15/10 ,  G10L15/14 ,  G10L15/16 ,  G10L15/32 ,  G10L15/06

摘要： Disclosed is a multi-device control method including: performing a voice recognition operation on a voice command generated from a sound source; identifying distances between each of the plurality of devices and the sound source; assigning response rankings to the devices by combining a context-specific correction score of each device corresponding to the voice command and the distances; and selecting a device to respond to the voice command from among the devices according to the response rankings.

公开(公告)号：US11151983B2

公开(公告)日：2021-10-19

申请号：US17105263

申请日：2020-11-25

申请人： Johnson Controls Technology Company

发明人： Youngchoon Park ,  Sudhi R. Sinha ,  Vaidhyanathan Venkiteswaran ,  Erik S. Paulson ,  Vijaya S. Chennupati

IPC分类号： G05B15/00 ,  G10L15/14 ,  G10L25/63 ,  G10L15/30 ,  G10L15/22 ,  G06F3/01 ,  G06F16/00

摘要： One or more non-transitory computer readable media contain program instructions that, when executed, cause one or more processors to: receive first raw data including one or more first data points generated by a first object of a plurality of objects associated with one or more buildings; generate first input timeseries according to the one or more data points; access a database of interconnected smart entities, the smart entities including object entities representing each of the plurality of objects and data entities representing stored data, the smart entities being interconnected by relational objects indicating relationships between the smart entities; identify a first object entity representing the first object from a first identifier in the first input timeseries; identify a first data entity from a first relational object indicating a relationship between the first object entity and the first data entity; and store the first input timeseries in the first data entity.

公开(公告)号：US20210287664A1

公开(公告)日：2021-09-16

申请号：US16817944

申请日：2020-03-13

申请人： Palo Alto Research Center Incorporated

发明人： Evgeniy Bart ,  Margaret H. Szymanski

IPC分类号： G10L15/14 ,  G06N20/00 ,  G06N3/08

摘要： Digitized media is received that records a conversation between individuals. Cues are extracted from the digitized media that indicate properties of the conversation. The cues are entered as training data into a machine learning module to create a trained machine learning model. The trained machine learning model is used in a processor to detect other misalignments in subsequent digitized conversations.

公开(公告)号：US11081106B2

公开(公告)日：2021-08-03

申请号：US15687202

申请日：2017-08-25

申请人： Microsoft Technology Licensing, LLC

发明人： Xihui Lin ,  Andrew James McNamara ,  Jing He

IPC分类号： G10L15/14 ,  G10L15/16 ,  G10L15/06 ,  G06N5/02 ,  G06F16/332 ,  G06F16/33 ,  G10L15/22 ,  G10L15/18 ,  G06F40/295 ,  G06N3/04 ,  G06N7/00 ,  G06F40/30

摘要： A spoken dialogue system includes a spoken language understanding apparatus. The spoken language understanding apparatus can include an intent apparatus and a selection apparatus. The intent apparatus is configured to determine if a query comprises a global command, to determine if an intent associated with a query is or is not included in a domain that is supported by the spoken dialogue system, to determine if a query comprises a confirmation type, to tag one or more entities in a query, and to determine an intent probability distribution and a domain probability distribution that is associated with a query. When the query includes an entity that is included in two or more possible entities, the selection apparatus is configured to provide a score for each of the two or more possible entities.

公开(公告)号：US20210183372A1

公开(公告)日：2021-06-17

申请号：US16717507

申请日：2019-12-17

申请人： Spotify AB

发明人： Andreas Jansson ,  Eric J. Humphrey ,  Rachel Malia Bittner ,  Sravana K. Reddy

IPC分类号： G10L15/08 ,  G10L15/187 ,  G10L15/14

摘要： Term masking is performed by generating a time-alignment value for a plurality of identifiable units of sound in vocal audio content contained in a mixed audio track, force-aligning each of the plurality of identifiable units of sound to the vocal audio content based on the time-alignment value, thereby generating a plurality of force-aligned identifiable units of sound, identifying from the plurality of force-aligned identifiable units of sound a force-aligned identifiable unit of sound to be muddled, and audio muddling the force-aligned identifiable unit of sound to be muddled.

公开(公告)号：US20210134277A1

公开(公告)日：2021-05-06

申请号：US16605025

申请日：2018-04-17

申请人： Oxford University Innovation Limited

发明人： Vipul ARORA ,  Aditi LAHIRI ,  Henning REETZ

IPC分类号： G10L15/187 ,  G10L15/16 ,  G10L15/22 ,  G10L15/02 ,  G10L15/14 ,  G09B19/04

摘要： A computer implemented method for automatic speech analysis comprising setting a target phrase, the target phrase comprising a target phoneme, the target phoneme having corresponding target values of a set of phonological features associated therewith, wherein each target value is one of: an indication that the phonological feature should be present, an indication that the phonological feature should be absent, or an indication that the presence of the phonological feature is not specified, receiving a speech signal, wherein the speech signal comprises a user's attempt to say the target phrase, analysing the speech signal to determine the phonological features present within a portion of the speech signal corresponding to the target phoneme and assigning a probability to each of the set of phonological features, comparing the probability assigned to each phonological feature based on the speech signal to the expected target value of that phonological feature within the phrase, determining a deviation from the comparison; and outputting the deviation to provide feedback on the closeness of the speech signal to the phrase.

公开(公告)号：US10991366B2

公开(公告)日：2021-04-27

申请号：US16025456

申请日：2018-07-02

申请人： SAMSUNG SDS CO., LTD.

发明人： Han Hoon Kang ,  Eun Hye Ji ,  Na Rae Kim ,  Jae Young Yang

IPC分类号： G10L15/18 ,  G06F16/9537 ,  G06Q30/02 ,  G06F16/35 ,  G10L13/02 ,  G10L15/19 ,  G10L15/14 ,  G10L15/22 ,  G10L15/26 ,  G06F40/35

摘要： A method, performed by a dialogue processing device, of processing dialogue associated with a user based on dialog act information, the method comprises receiving speech information, corresponding to speech of the user, including a plurality of sentence units; identifying a first sentence unit and a second sentence unit, of the plurality of sentence units, based on receiving the speech information; extracting a first dialog act indicative of an intention of the first sentence unit and extracting a second dialog act indicative of an intention of the second sentence unit; extracting a first dialog act indicative of an intention of the first sentence unit and extracting a second dialog act indicative of an intention of the second sentence unit; processing the first sentence unit and the second unit in a sequence according to respective priority orders assigned based on a number of empty slots of dialogue frames of the sentence units.