中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

74 records (took 0.056 seconds)

    Interpreting Expressions Having Potentially Ambiguous Meanings In Different Domains
    31.
    发明申请
    Interpreting Expressions Having Potentially Ambiguous Meanings In Different Domains 审中-公开

    公开(公告)号：US20190303438A1

    公开(公告)日：2019-10-03

    申请号：US15942875

    申请日：2018-04-02

    Applicant: SoundHound, Inc.

    Inventor： Christopher S. Wilson ,  Keyvan Mohajer ,  Bernard Mont-Reynaud

    IPC: G06F17/27 ,  G10L15/22 ,  G10L15/18 ,  G10L15/30

    Abstract: The present invention extends to methods, systems, and computer program products for interpreting expressions having potentially ambiguous meanings in different domains. Multi-domain natural language understanding systems can support a variety of different types of clients. Expressions can be interpreted across multiple domains. Weights can be assigned to domains. Weights can be client specific or expression specific so that a chosen interpretation is more likely correct for the type of client or for its context. Stored weight sets can be chosen according to identifying information carried as metadata with expressions or weight sets carried directly as metadata. Domains can additionally or alternatively be ranked in ordered lists or comparative domain pairs of to favor some domains over others as appropriate for client type or client context.

    Dual mode speech recognition
    32.
    发明授权
    Dual mode speech recognition 有权

    公开(公告)号：US10410635B2

    公开(公告)日：2019-09-10

    申请号：US15619304

    申请日：2017-06-09

    Applicant: SoundHound, Inc.

    Inventor： Bernard Mont-Reynaud

    IPC: G10L15/22 ,  G10L15/02 ,  G10L15/00 ,  G10L15/32 ,  G10L15/06 ,  G10L15/30 ,  G10L15/18

    Abstract: A dual mode speech recognition system sends speech to two or more speech recognizers. If a first recognition result is received, whose recognition score exceeds a high threshold, the first result is selected without waiting for another result. If the score is below a low threshold, the first result is ignored. At intermediate values of recognition scores, a timeout duration is dynamically determined as a function of the recognition score. The timeout duration determines how long the system will wait for another result. Many functions of the recognition score are possible, but timeout durations generally decrease as scores increase. When receiving a second recognition score before the timeout occurs, a comparison based on recognition scores determines whether the first result or the second result is the basis for creating a response.

    Predicting human behavior by machine learning of natural language interpretations
    33.
    发明授权
    Predicting human behavior by machine learning of natural language interpretations 有权

    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.

    PARAMETRIC ADAPTATION OF VOICE SYNTHESIS
    34.
    发明申请
    PARAMETRIC ADAPTATION OF VOICE SYNTHESIS 审中-公开

    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.

    Natural Language Module Store
    36.
    发明申请
    Natural Language Module Store 审中-公开

    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.

    Method and system for building an integrated user profile
    37.
    发明授权
    Method and system for building an integrated user profile 有权
    构建集成用户配置文件的方法和系统

    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。

    System and method for matching a query against a broadcast stream
    38.
    发明授权
    System and method for matching a query against a broadcast stream 有权
    用于将查询与广播流匹配的系统和方法

    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。

    System and method for performing dual mode speech recognition
    39.
    发明授权
    System and method for performing dual mode speech recognition 有权
    用于执行双模式语音识别的系统和方法

    公开(公告)号：US09330669B2

    公开(公告)日：2016-05-03

    申请号：US14621024

    申请日：2015-02-12

    Applicant: SoundHound, Inc.

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

    IPC: G10L15/04 ,  G10L15/00 ,  G10L15/30 ,  G10L15/08 ,  G10L15/26 ,  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.

    Abstract translation: 提出了一种用于执行双模式语音识别的系统和方法，在移动设备上使用本地识别模块和在服务器设备上使用远程识别引擎。 该系统接受来自用户的口语查询，并且本地识别模块和远程识别引擎都对查询执行语音识别操作，返回转录和置信度得分，并受到延迟截止时间的限制。 如果两个来源成功地转录查询，则系统接受具有较高置信度得分的结果。 如果只有一个源成功，则该结果被接受。 在任一情况下，如果远程识别引擎确实成功地转录查询，则如果远程系统结果包括客户端词汇中不存在的信息，则更新客户词汇。

Patent Agency Ranking