中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

192 records (took 0.032 seconds)

    Training a transcription system
    121.
    发明授权
    Training a transcription system 有权
    训练转录系统

    公开(公告)号：US09009040B2

    公开(公告)日：2015-04-14

    申请号：US12774054

    申请日：2010-05-05

    Applicant: Todd C. Tatum ,  Michael A. Ramalho ,  Paul M. Dunn ,  Shantanu Sarkar ,  Tyrone T. Thorsen ,  Alan D. Gatzke

    Inventor： Todd C. Tatum ,  Michael A. Ramalho ,  Paul M. Dunn ,  Shantanu Sarkar ,  Tyrone T. Thorsen ,  Alan D. Gatzke

    IPC: G10L15/00 ,  G10L15/07 ,  G10L15/06

    CPC classification number: G10L15/07 ,  G10L2015/0638

    Abstract: According to certain embodiments, training a transcription system includes accessing recorded voice data of a user from one or more sources. The recorded voice data comprises voice samples. A transcript of the recorded voice data is accessed. The transcript comprises text representing one or more words of each voice sample. The transcript and the recorded voice data are provided to a transcription system to generate a voice profile for the user. The voice profile comprises information used to convert a voice sample to corresponding text.

    Abstract translation: 根据某些实施例，训练转录系统包括从一个或多个来源访问用户的记录语音数据。 记录的语音数据包括语音样本。 录制的语音数据的记录被访问。 成绩单包括表示每个语音样本的一个或多个单词的文本。 将转录本和记录的语音数据提供给转录系统以生成用户的语音简档。 语音简档包括用于将语音样本转换为相应文本的信息。

    Customized ring tones for mobile phones based on context information
    122.
    发明授权
    Customized ring tones for mobile phones based on context information 有权

    公开(公告)号：US08977249B2

    公开(公告)日：2015-03-10

    申请号：US12157569

    申请日：2008-06-11

    Applicant: Shantanu Sarkar ,  Joseph Brian Burton

    Inventor： Shantanu Sarkar ,  Joseph Brian Burton

    IPC: H04M3/42 ,  H04M3/02

    CPC classification number: H04M3/02 ,  H04M3/42042 ,  H04M3/42051

    Abstract: A method in one embodiment includes receiving, by a mobile client device, an incoming call sent by a caller, a caller ID being associated with the incoming call. A node connected to a packet-based network is accessed to obtain information about the caller. Information about the caller is then received from the node by the mobile client device. This information is applied to a set of client rules that selects a specific ring tone from a plurality of ring tones stored on the mobile client device. Finally, the specific ring tone is generated on the mobile client device to announce the incoming call.

    Method and apparatus for enhancing speaker selection
    123.
    发明授权
    Method and apparatus for enhancing speaker selection 有权
    用于增强扬声器选择的方法和装置

    公开(公告)号：US08971511B2

    公开(公告)日：2015-03-03

    申请号：US11278371

    申请日：2006-03-31

    Applicant: Shmuel Shaffer ,  Shantanu Sarkar ,  Labhesh Patel

    Inventor： Shmuel Shaffer ,  Shantanu Sarkar ,  Labhesh Patel

    IPC: H04M3/42 ,  H04M3/56

    CPC classification number: H04M3/56 ,  H04L12/1822 ,  H04M3/42187 ,  H04M3/566 ,  H04M2203/5072 ,  H04M2242/06

    Abstract: A method and apparatus to provide speaker selection in a multi-party conference call is described. The method may comprise processing a speaker queue for at least one new speaker and monitoring when a number of active speakers is less than a predetermined number of active speakers. When less than the predetermined number, the method automatically, without human intervention, adds a new speaker from the speaker queue. A request for a new speaker may be received via a communication channel independent of a voice communication channel of the multi-party conference call. The request may be received from the conference endpoint via a voice communication channel of the multi-party conference call. In an example embodiment, new speakers in the speaker queue may be prioritized based a class of service associated with each new speaker. Priority may be given to a new speaker with a higher associated class of service.

    Abstract translation: 描述了在多方电话会议中提供说话者选择的方法和装置。 该方法可以包括处理用于至少一个新扬声器的扬声器队列，并且当多个有源扬声器小于预定数量的有源扬声器时进行监视。 当小于预定数量时，该方法在没有人为干预的情况下自动地从扬声器队列添加新的扬声器。 可以通过独立于多方电话会议的语音通信信道的通信信道来接收对新的扬声器的请求。 可以经由多方电话会议的语音通信信道从会议端点接收该请求。 在示例性实施例中，可以基于与每个新的说话者相关联的一类服务对扬声器队列中的新扬声器进行优先级排序。 可以优先考虑具有较高相关服务类别的新发言者。

    Speaker-cluster dependent speaker recognition (speaker-type automated speech recognition)
    126.
    发明授权
    Speaker-cluster dependent speaker recognition (speaker-type automated speech recognition) 有权
    扬声器群集相关扬声器识别（扬声器型自动语音识别）

    公开(公告)号：US08600750B2

    公开(公告)日：2013-12-03

    申请号：US12795959

    申请日：2010-06-08

    Applicant: Michael A. Ramalho ,  Todd C. Tatum ,  Shantanu Sarkar

    Inventor： Michael A. Ramalho ,  Todd C. Tatum ,  Shantanu Sarkar

    IPC: G10L15/06

    CPC classification number: G10L15/075 ,  G10L2015/0631

    Abstract: In an example embodiment, there is disclosed herein an automatic speech recognition (ASR) system that employs speaker clustering (or speaker type) for transcribing audio. A large corpus of audio with corresponding transcripts is analyzed to determine a plurality of speaker types (e.g., dialects). The ASR system is trained for each speaker type. Upon encountering a new user, the ASR system attempts to map the user to a speaker type. After the new user is mapped to a speaker type, the ASR employs the speaker type for transcribing audio from the new user.

    Abstract translation: 在示例实施例中，这里公开了一种使用用于转录音频的扬声器聚类（或扬声器类型）的自动语音识别（ASR）系统。 分析具有对应的抄本的大的音频语料库以确定多个扬声器类型（例如，方言）。 针对每个扬声器类型训练ASR系统。 在遇到新用户时，ASR系统尝试将用户映射到扬声器类型。 在新用户映射到扬声器类型之后，ASR使用扬声器类型从新用户转录音频。

    Capturing and controlling access to muted content from a conference session
    127.
    发明授权
    Capturing and controlling access to muted content from a conference session 有权
    从会议会话中获取并控制对静音内容的访问

    公开(公告)号：US08553067B2

    公开(公告)日：2013-10-08

    申请号：US12828625

    申请日：2010-07-01

    Applicant: Shmuel Shaffer ,  Jochen Weppner ,  Shantanu Sarkar ,  Mukul Jain

    Inventor： Shmuel Shaffer ,  Jochen Weppner ,  Shantanu Sarkar ,  Mukul Jain

    IPC: H04N7/15 ,  H04M3/00 ,  H04L12/26 ,  G06F15/16

    CPC classification number: H04N7/15 ,  H04N7/147 ,  H04N7/155

    Abstract: Techniques are provided for receiving multimedia from a plurality of endpoints participating in a conference session, including multimedia from an endpoint that was muted during the conference session. A muting state is detected at a particular endpoint during the conference session and the multimedia from the particular endpoint is recorded even though it is not forwarded and rendered to the other endpoints during the conference session. Information associated with the multimedia data for the conference session is stored to indicate the time period during which the muting state was detected at the particular endpoint. Techniques are also provided for granting access at a later time to the stored multimedia data for conference session, including access controls to the muted multimedia.

    Abstract translation: 提供技术用于从参与会议会话的多个端点接收多媒体，包括来自在会议期间被静音的端点的多媒体。 在会议会话期间在特定端点处检测到静音状态，并且即使在会议会话期间不转发并呈现给其他端点，也记录来自特定端点的多媒体。 存储与会议会话的多媒体数据相关联的信息，以指示在特定端点处检测到静音状态的时间段。 还提供了用于在稍后时间将存储的多媒体数据用于会议会话的准许技术，包括对静音多媒体的访问控制。

    Reducing power consumption of wireless devices
    128.
    发明授权
    Reducing power consumption of wireless devices 有权
    降低无线设备的功耗

    公开(公告)号：US08515411B2

    公开(公告)日：2013-08-20

    申请号：US13617655

    申请日：2012-09-14

    Applicant: Shantanu Sarkar ,  Roger Chi-yee Cheung ,  Morris J. Katz

    Inventor： Shantanu Sarkar ,  Roger Chi-yee Cheung ,  Morris J. Katz

    IPC: H04M3/00

    CPC classification number: H04W88/06 ,  H04W52/0274 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/162 ,  Y02D70/164 ,  Y02D70/166

    Abstract: Described in example embodiments herein are techniques that combine at least two network (communication) technologies (such as protocols, signaling methods, etc.) and limit when a wireless device employs one of the technologies. In an example embodiment, a passive technology, such as a Radio Frequency Identification (RFID) technology, can be employed to determine whether a certain network technology is available.

    Abstract translation: 在本文的示例性实施例中描述的是组合至少两个网络（通信）技术（诸如协议，信令方法等）的技术，并且限制当无线设备采用其中一种技术时。 在示例性实施例中，可以采用诸如射频识别（RFID）技术的无源技术来确定某种网络技术是否可用。

    Method and apparatus for conference spanning
    129.
    发明授权
    Method and apparatus for conference spanning 有权
    会议跨越的方法和装置

    公开(公告)号：US08483098B2

    公开(公告)日：2013-07-09

    申请号：US11288690

    申请日：2005-11-29

    Applicant: Sravan Vadlakonda ,  Shantanu Sarkar ,  Ashish Chotai ,  Aseem Asthana ,  Glenn Inn

    Inventor： Sravan Vadlakonda ,  Shantanu Sarkar ,  Ashish Chotai ,  Aseem Asthana ,  Glenn Inn

    IPC: H04L12/16 ,  H04Q11/00

    CPC classification number: H04N7/15 ,  H04L12/1827

    Abstract: Disclosed are conferencing systems, devices, architectures, and methods for managing a conference spanning system to facilitate participation in a plurality of conferences at the same time. An exemplary system having devices and/or structures in accordance with embodiments can include: (i) a plurality of conferences, each conference being configured to support a plurality of media modes; (ii) a presentation mechanism configured to support the plurality of media modes from the plurality of conferences; and (iii) a selector for selecting a conference from the plurality of conferences and designating the selected conference as an active conference and designating non-selected conferences as background conferences, wherein the active conference is assigned at least one enhanced media mode in the presentation mechanism.

    Abstract translation: 公开了用于管理会议跨越系统以便于同时参与多个会议的会议系统，设备，架构和方法。 具有根据实施例的设备和/或结构的示例性系统可以包括：（i）多个会议，每个会议被配置为支持多个媒体模式; （ii）呈现机构，被配置为从所述多个会议中支持所述多个媒体模式; 以及（iii）选择器，用于从所述多个会议中选择会议，并将所选择的会议指定为活动会议并指定未选择的会议作为背景会议，其中所述活动会议在所述呈现机制中被分配至少一个增强媒体模式 。

Patent Agency Ranking