公开(公告)号：US20190244600A1

公开(公告)日：2019-08-08

申请号：US16388753

申请日：2019-04-18

Applicant: SoundHound, Inc.

Inventor： Jun HUANG ,  Kiran Garaga LOKESWARAPPA ,  Joel GEDALIUS ,  Bernard MONT-REYNAUD

IPC: G10L15/02 ,  G06N20/00 ,  H04L29/08 ,  G10L25/90 ,  G10L15/06 ,  G06Q30/02 ,  G06F17/27 ,  G10L15/18

CPC classification number: G10L15/02 ,  G06F17/2705 ,  G06F17/271 ,  G06F17/274 ,  G06N20/00 ,  G06Q30/0251 ,  G06Q30/0276 ,  G06Q30/0277 ,  G10L15/063 ,  G10L15/1815 ,  G10L15/22 ,  G10L15/26 ,  G10L25/51 ,  G10L25/90 ,  G10L2015/025 ,  H04L67/306

Abstract: A method is provided for advertisement selection. The method includes recognizing words from user speech over a large number of interactions, computing a number of unique words uttered during the interactions, classifying the user by the number of unique words uttered during the interactions, and selecting an advertisement targeted to the classified users.

公开(公告)号：US10296586B2

公开(公告)日：2019-05-21

申请号：US15425099

申请日：2017-02-06

Applicant: SoundHound, Inc.

Inventor： Pranav Singh ,  Bernard Mont-Reynaud ,  Kheng Khov ,  Jonah Probell

IPC: G10L15/00 ,  G10L15/18 ,  G10L25/63 ,  G06F17/27 ,  G06Q30/02 ,  G06F16/00 ,  G06F16/29 ,  G06F16/9537

Abstract: An accurate thought map is created by recording people's many utterances of natural language expressions together with the location at which each expression was made. The expressions are input into a Natural Language Understanding system including a semantic parser, and the resulting interpretations stored in a database with the geolocation of the speaker. Emotions, concepts, time, user identification, and other interesting information may also be detected and stored. Interpretations of related expressions may be linked in the database. The database may be indexed and filtered according to multiple aspects of interpretations such as geolocation ranges, time ranges or other criteria, and analyzed according to multiple algorithms. The analyzed results may be used to render map displays, determine effective locations for advertisements, preemptively fetch information for users of mobile devices, and predict the behavior of individuals and groups of people.

公开(公告)号：US20190035386A1

公开(公告)日：2019-01-31

申请号：US16147892

申请日：2018-10-01

Applicant: SoundHound, Inc.

Inventor： Rainer LEEB ,  Stephanie LAWSON ,  Kamyar MOHAJER ,  Glenda MOSLEY

IPC: G10L15/01 ,  G10L15/06

Abstract: A speech and natural language-based virtual assistant parses user utterances and analyzes them in the context of recent prior actions to detect sentiment and indicators of satisfaction or dissatisfaction. Indicators are stored in a database in association with the prior command and resulting action. Databases can include timestamps, clarifications made by users, and a knowledge graph of facts. Machine learning, applied to the database, train models to deliver improved results in future user engagements.

公开(公告)号：US20180261216A1

公开(公告)日：2018-09-13

申请号：US15456354

申请日：2017-03-10

Applicant: SoundHound, Inc.

Inventor： Rainer Leeb

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

CPC classification number: G10L15/22 ,  G06F17/2785 ,  G10L15/1815 ,  G10L2015/221

Abstract: Systems perform methods of interpreting spoken utterances from a user and responding to the utterances by providing requested information or performing a requested action. The utterances are interpreted in the context of multiple domains. Each interpretation is assigned a relevancy score based on how well the interpretation represents what the speaker intended. Interpretations having a relevancy score below a threshold for its associated domain are discarded. A remaining interpretation is chosen based on choosing the most relevant domain for the utterance. The user may be prompted to provide disambiguation information that can be used to choose the best domain. Storing past associations of utterance representation and domain choice allows for measuring the strength of correlation between uttered words and phrases with relevant domains. This correlation strength information may allow the system to automatically disambiguate alternate interpretations without requiring user input.

公开(公告)号：US20180182373A1

公开(公告)日：2018-06-28

申请号：US15406213

申请日：2017-01-13

Applicant: SoundHound, Inc.

Inventor： Monika Almudafar-Depeyrot ,  Bernard Mont-Reynaud

IPC: G10L13/033 ,  G10L13/10 ,  G10L13/047 ,  G06F17/27

CPC classification number: G06F17/2785 ,  G10L13/00

Abstract: Software-based systems perform parametric speech synthesis. TTS voice parameters determine the generated speech audio. Voice parameters include gender, age, dialect, donor, arousal, authoritativeness, pitch, range, speech rate, volume, flutter, roughness, breath, frequencies, bandwidths, and relative amplitudes of formants and nasal sounds. The system chooses TTS parameters based on one or more of: user profile attributes including gender, age, and dialect; situational attributes such as location, noise level, and mood; natural language semantic attributes such as domain of conversation, expression type, dimensions of affect, word emphasis and sentence structure; and analysis of target speaker voices. The system chooses TTS parameters to improve listener satisfaction or other desired listener behavior. Choices may be made by specified algorithms defined by code developers, or by machine learning algorithms trained on labeled samples of system performance.

公开(公告)号：US20180108343A1

公开(公告)日：2018-04-19

申请号：US15294234

申请日：2016-10-14

Applicant: SoundHound, Inc.

Inventor： Mark Stevans ,  Monika Almudafar-Depeyrot ,  Keyvan Mohajer

IPC: G10L13/08 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L15/02

CPC classification number: G10L13/08 ,  G10L13/043 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/025 ,  G10L2015/088 ,  G10L2015/223

Abstract: A speech-enabled dialog system responds to a plurality of wake-up phrases. Based on which wake-up phrase is detected, the system's configuration is modified accordingly. Various configurable aspects of the system include selection and morphing of a text-to-speech voice; configuration of acoustic model, language model, vocabulary, and grammar; configuration of a graphic animation; configuration of virtual assistant personality parameters; invocation of a particular user profile; invocation of an authentication function; and configuration of an open sound. Configuration depends on a target market segment. Configuration also depends on the state of the dialog system, such as whether a previous utterance was an information query.

公开(公告)号：US09691390B2

公开(公告)日：2017-06-27

申请号：US15085944

申请日：2016-03-30

Applicant: SoundHound, Inc.

Inventor： Timothy Stonehocker ,  Keyvan Mohajer ,  Bernard Mont-Reynaud

IPC: G10L15/04 ,  G10L15/00 ,  G10L15/30 ,  G10L15/08 ,  G10L15/26 ,  G10L15/06 ,  G10L17/06 ,  G10L15/34

CPC classification number: G10L15/30 ,  G10L15/04 ,  G10L15/063 ,  G10L15/08 ,  G10L15/265 ,  G10L15/34 ,  G10L17/06 ,  G10L2015/0635 ,  G10L2015/081

Abstract: A system and method is presented for performing dual mode speech recognition, employing a local recognition module on a mobile device and a remote recognition engine on a server device. The system accepts a spoken query from a user, and both the local recognition module and the remote recognition engine perform speech recognition operations on the query, returning a transcription and confidence score, subject to a latency cutoff time. If both sources successfully transcribe the query, then the system accepts the result having the higher confidence score. If only one source succeeds, then that result is accepted. In either case, if the remote recognition engine does succeed in transcribing the query, then a client vocabulary is updated if the remote system result includes information not present in the client vocabulary.

公开(公告)号：US20170154628A1

公开(公告)日：2017-06-01

申请号：US14954810

申请日：2015-11-30

Applicant: SoundHound Inc.

Inventor： Keyvan Mohajer ,  Kamyar Mohajer ,  Bernard Mont-Reynaud ,  Pranav Singh

IPC: G10L15/30 ,  G06Q30/02 ,  G06Q20/10 ,  G06F17/28

CPC classification number: G06F17/28 ,  G06F17/271 ,  G06Q30/0283 ,  G10L15/30

Abstract: The present invention extends to methods, systems, and computer program products for a natural language module store. In general, the invention can be used to manage natural language modules offered through a natural language module store. Natural language module (NLM) developers can post NLMs at a NLM store to make the NLMs available for use by others. Developers can select NLMs for inclusion in natural language interpreters (NLIs) containing (and possibly integrating the functionality of) one or more NLMs. Prior to selecting a NLM, a developer can search or browse NLMs to identify an appropriate NLM. Optionally, a developer can test a NLM in the NLM store prior to inclusion in an NLI. For example, multiple NLMs purporting to provide the same specified natural language functionality can be tested relative to one another prior to selection of one of the NLMs for inclusion in an NLI.

公开(公告)号：US09564123B1

公开(公告)日：2017-02-07

申请号：US14704833

申请日：2015-05-05

Applicant: SoundHound, Inc.

Inventor： Bernard Mont-Reynaud ,  Jun Huang ,  Kiran Garaga Lokeswarappa ,  Joel Gedalius

IPC: G10L15/06 ,  G10L15/02 ,  H04L29/08 ,  G06F17/27 ,  G10L15/22

CPC classification number: H04L67/306 ,  G06F17/271 ,  G06Q30/0277 ,  G10L15/063 ,  G10L15/07 ,  G10L15/22 ,  G10L25/51

Abstract: A system and method are provided for adding user characterization information to a user profile by analyzing user's speech. User properties such as age, gender, accent, and English proficiency may be inferred by extracting and deriving features from user speech, without the user having to configure such information manually. A feature extraction module that receives audio signals as input extracts acoustic, phonetic, textual, linguistic, and semantic features. The module may be a system component independent of any particular vertical application or may be embedded in an application that accepts voice input and performs natural language understanding. A profile generation module receives the features extracted by the feature extraction module and uses classifiers to determine user property values based on the extracted and derived features and store these values in a user profile. The resulting profile variables may be globally available to other applications.

Abstract translation: 提供了一种系统和方法，用于通过分析用户的语音将用户表征信息添加到用户简档。 用户属性如年龄，性别，口音和英语水平可以通过从用户语音中提取和导出特征来推断，而用户不必手动配置此类信息。 接收音频信号作为输入的特征提取模块提取声，语音，文本，语言和语义特征。 模块可以是独立于任何特定垂直应用的系统组件，或者可以嵌入在接受语音输入并执行自然语言理解的应用中。 简档生成模块接收由特征提取模块提取的特征，并使用分类器基于提取和导出的特征来确定用户属性值，并将这些值存储在用户简档中。 所得到的概要文件变量可能全局可用于其他应用程序。

公开(公告)号：US09563699B1

公开(公告)日：2017-02-07

申请号：US14692310

申请日：2015-04-21

Applicant: SoundHound Inc.

Inventor： Keyvan Mohajer ,  Bernard Mont-Reynaud ,  Joe Kyaw Soe Aung

IPC: G06F17/30 ,  H04H60/35 ,  H04H60/27 ,  H04H60/13 ,  G10L19/018 ,  H04H60/44 ,  H04H60/43 ,  H04H20/14

CPC classification number: G06F17/30752 ,  G06F17/30743 ,  G06F17/30772 ,  G10L19/018 ,  H04H20/14 ,  H04H60/13 ,  H04H60/27 ,  H04H60/35 ,  H04H60/372 ,  H04H60/43 ,  H04H60/44 ,  H04H60/58

Abstract: A method for matching a query against a broadcast stream includes receiving one or more broadcast streams, from which it generates and stores an audio fingerprint of a selected portion of each received broadcast stream. A query is received from which the method generates an audio fingerprint. From that point, the method continues by identifying audio content from the query, using the query audio fingerprint and a database of indexed audio content. The method concludes by identifying the source of the query using the query audio fingerprint and the stored audio fingerprints. Embodiments of the method further include predictively caching audio fingerprint sequences and corresponding audio item identifiers from a server after storing audio fingerprints extracted from the broadcast stream; and using the predictively cached audio fingerprint sequences to identify an audio item within the audio signal based on at least some additional audio fingerprints of the audio signal.

Abstract translation: 用于将查询与广播流匹配的方法包括接收一个或多个广播流，从而生成并存储每个接收的广播流的所选部分的音频指纹。 接收到该方法生成音频指纹的查询。 从那时起，该方法通过使用查询音频指纹和索引的音频内容的数据库识别来自查询的音频内容来继续。 该方法通过使用查询音频指纹和存储的音频指纹识别查询的来源得出结论。 该方法的实施例还包括在存储从广播流中提取的音频指纹之后，从服务器预测性地缓存音频指纹序列和对应的音频项目标识符; 以及使用所述预测缓存的音频指纹序列基于所述音频信号的至少一些附加音频指纹来识别所述音频信号内的音频项目。