公开(公告)号：US20240144921A1

公开(公告)日：2024-05-02

申请号：US18050182

申请日：2022-10-27

Applicant: SoundHound, Inc.

Inventor： Pranav SINGH ,  Yilun ZHANG ,  Eunjee NA ,  Olivia BETTAGLIO

IPC: G10L15/18 ,  G10L15/06 ,  G10L15/22

CPC classification number: G10L15/1815 ,  G10L15/063 ,  G10L15/1822 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/223

Abstract: Automatically generating sentences that a user can say to invoke a set of defined actions performed by a virtual assistant are disclosed. A sentence is received and keywords are extracted from the sentence. Based on the keywords, additional sentences are generated. A classifier model is applied to the generated sentences to determine a sentence that satisfies a threshold. In the situation a sentence satisfies the threshold, an intent associated with the classifier model can be invoked. In the situation the sentences fail to satisfy the classifier model, the virtual assistant can attempt to interpret the received sentence according to the most likely intent by invoking a sentence generation model fine-tuned for a particular domain, generate additional sentences with a high probability of having the same intent and fulfill the specific action defined by the intent.

公开(公告)号：US20210397610A1

公开(公告)日：2021-12-23

申请号：US17350294

申请日：2021-06-17

Applicant: SoundHound, Inc.

Inventor： Pranav SINGH ,  Yilun ZHANG ,  Keyvan MOHAJER ,  Mohammadreza FAZELI

IPC: G06F16/242 ,  G06N3/04 ,  G06N3/08

Abstract: A machine learning system for a digital assistant is described, together with a method of training such a system. The machine learning system is based on an encoder-decoder sequence-to-sequence neural network architecture trained to map input sequence data to output sequence data, where the input sequence data relates to an initial query and the output sequence data represents canonical data representation for the query. The method of training involves generating a training dataset for the machine learning system. The method involves clustering vector representations of the query data samples to generate canonical-query original-query pairs in training the machine learning system.

公开(公告)号：US20190163743A1

公开(公告)日：2019-05-30

申请号：US16244039

申请日：2019-01-09

Applicant: SoundHound, Inc.

Inventor： Kheng KHOV ,  Pranav SINGH ,  Bernard MONT-REYNAUD ,  Jonah PROBELL

IPC: G06F17/27 ,  G06F16/00 ,  G06F16/9537 ,  G06F16/29 ,  G06Q30/02

Abstract: A method of determining a count of occurrences of concepts within regions is provided. The method includes receiving natural language expressions, each expression being uttered by a person located at a different geolocation, receiving geolocation information of each person having uttered the natural language expressions and associating the geolocation information of each person with a corresponding natural language expression and for each natural language expression: parsing the natural language expression to create an interpretation, deriving concepts, and recording, in a database, concepts, geolocation, and associations of the concepts and geolocations; and accumulating, for each region, a count of occurrences of each concept having an associated geolocation within the region.

公开(公告)号：US20220165257A1

公开(公告)日：2022-05-26

申请号：US17455727

申请日：2021-11-19

Applicant: SoundHound, Inc.

Inventor： Pranav SINGH ,  Keyvan MOHAJER ,  Yilun ZHANG

IPC: G10L15/18 ,  G10L15/06 ,  G10L15/02 ,  G10L15/22

Abstract: Methods and systems for automatically generating sample phrases or sentences that a user can say to invoke a set of defined actions performed by a virtual assistant are disclosed. By enabling finetuned general-purpose natural language models, the system can generate potential and accurate utterance sentences based on extracted keywords or the input utterance sentence. Furthermore, domain-specific datasets can be used to train the pre-trained, general-purpose natural language models via unsupervised learning. These generated sentences can improve the efficiency of configuring a virtual assistant. The system can further optimize the effectiveness of a virtual assistant in understanding the user, which can enhance the user experience of communicating with it.

公开(公告)号：US20190138602A1

公开(公告)日：2019-05-09

申请号：US16238445

申请日：2019-01-02

Applicant: SoundHound, Inc.

Inventor： Kheng KHOV ,  Pranav SINGH ,  Bernard MONT-REYNAUD ,  Jonah PROBELL

IPC: G06F17/27 ,  G06F16/9537 ,  G06F16/29 ,  G06Q30/02 ,  G06F16/00

Abstract: A method of predicting a person's interests is provided. The method includes receiving geolocation information about a user location, reading, from a database of interpretations, at least one interpretation of an expression made in close proximity to the location, reading, from a database of ad bids, a plurality of ad bids comprising interpretations, comparing the interpretation from the database to the interpretations of the ad bids to select a most valuable ad bid having an interpretation that matches the interpretation of an expression made in close proximity to the location, and presenting an ad associated with the most valuable ad bid, wherein the interpretation is from a natural language expression.

公开(公告)号：US20230245649A1

公开(公告)日：2023-08-03

申请号：US17649810

申请日：2022-02-03

Applicant: SoundHound, Inc.

Inventor： Pranav SINGH ,  Saraswati MISHRA ,  Eunjee NA

IPC: G10L15/18 ,  G10L15/02 ,  G10L15/26

CPC classification number: G10L15/1815 ,  G10L15/02 ,  G10L15/26 ,  G10L2015/025

Abstract: Methods and systems for correction of a likely erroneous word in a speech transcription are disclosed. By evaluating token confidence scores of individual words or phrases, the automatic speech recognition system can replace a low-confidence score word with a substitute word or phrase. Among various approaches, neural network models can be used to generate individual confidence scores. Such word substitution can enable the speech recognition system to automatically detect and correct likely errors in transcription. Furthermore, the system can indicate the token confidence scores on a graphic user interface for labeling and dictionary enhancement.

公开(公告)号：US20220075956A1

公开(公告)日：2022-03-10

申请号：US17527154

申请日：2021-11-15

Applicant: SoundHound, Inc.

Inventor： Bernard MONT-REYNAUD ,  Jonah PROBELL ,  Pranav SINGH ,  Kheng KHOV

IPC: G06F40/30 ,  G06Q30/02 ,  G06F16/00 ,  G06F16/29 ,  G06F16/9537 ,  G06F40/289

Abstract: A method of providing relevant messages to an automotive virtual assistant is provided. The method includes receiving a spoken utterance and corresponding first geolocation information detected by a subsystem of a first automobile, parsing the spoken utterance to determine concepts and storing the concepts in a concept database indexed by the corresponding first geolocation information. The method further includes receiving second geolocation information detected by a subsystem of a second automobile, searching the concept database for an index based on the second geolocation information to find a stored concept of the stored concepts, searching a natural language expression database using the stored concept as an index to find an assistive natural language expression, wherein the assistive natural language expression includes a constituent part, and sending the assistive natural language expression to the second automobile with the stored concept in place of the constituent part.