公开(公告)号：WO2007008312A3

公开(公告)日：2007-01-18

申请号：PCT/US2006/021968

申请日：2006-06-06

Applicant: MOTOROLA, INC. ,  ROKUSEK, Daniel, S. ,  KAMBHAMPATI, Kranti, K. ,  PIKET, James, B. ,  SRENGER, Edward

Inventor： ROKUSEK, Daniel, S. ,  KAMBHAMPATI, Kranti, K. ,  PIKET, James, B. ,  SRENGER, Edward

IPC: H04Q7/20

Abstract: An apparatus and method for enhancing a handheld communication device via a telematics system in a vehicle is disclosed. Audio received at the handheld device is transferred to the telematics system in the vehicle. The received audio is then analyzed to determine whether it contains speech, and if so, an audio present signal is generated and the received audio is recorded into a memory coupled to the telematics system. The user can then engage the user interface of the telematics system to replay the recorded audio. Bluetooth protocol is preferably used to establish a channel between the handheld device and the telematics system, which can occur automatically when the two are in proximity. Analysis of the received audio preferably comprises use of a voice detector as part of a speech recognition system otherwise used by the telematics system to assess spoken commands.

公开(公告)号：WO2007106758A3

公开(公告)日：2007-09-20

申请号：PCT/US2007/063751

申请日：2007-03-12

Applicant: MOTOROLA, INC. ,  ISAAC, Emad, S. ,  ROKUSEK, Daniel, S. ,  SRENGER, Edward

Inventor： ISAAC, Emad, S. ,  ROKUSEK, Daniel, S. ,  SRENGER, Edward

IPC: G10L19/00

Abstract: A method of providing information storage by means of Automatic Speech Recognition through a communication device of a vehicle comprises establishing a voice communication between an external source and a user of the vehicle, receiving information from the external source, processing the received information using an Automatic Speech Recognition unit in the vehicle and storing the recognized speech in textual form for future retrieval or use.

公开(公告)号：EP1866743A2

公开(公告)日：2007-12-19

申请号：EP06720930.4

申请日：2006-02-21

Applicant: Motorola, Inc.

Inventor： SRENGER, Edward ,  ROKUSEK, Daniel, S. ,  WEIRICH, Kevin, L.

IPC: G06F9/00

CPC classification number: G06F9/453

Abstract: A method and apparatus for adapting a help menu on a user interface, utilizing an input method such as a speech recognition system, for increased efficiency. A list of menu items is presented on the user interface including an optional menu item to reinstate any previously removed menu items. A user selects an item from the menu, such as a help menu, which can then be removed from the list of menu items in accordance with predetermined criteria. The criteria can include how many times the menu item has been accessed and when. In this way, help menu items that are familiar to a user are removed to provide an abbreviated help menu which is more efficient and less frustrating to a user, particularly in a busy and distracting environment such as a vehicle.

公开(公告)号：EP1999746A2

公开(公告)日：2008-12-10

申请号：EP07758310.2

申请日：2007-03-12

Applicant: Motorola, Inc.

Inventor： ISAAC, Emad, S. ,  ROKUSEK, Daniel, S. ,  SRENGER, Edward

IPC: G10L19/00

CPC classification number: G10L15/22

Abstract: A method of providing information storage by means of Automatic Speech Recognition through a communication device of a vehicle comprises establishing a voice communication between an external source and a user of the vehicle, receiving information from the external source, processing the received information using an Automatic Speech Recognition unit in the vehicle and storing the recognized speech in textual form for future retrieval or use.

公开(公告)号：EP0764319A1

公开(公告)日：1997-03-26

申请号：EP96910297.0

申请日：1996-01-29

Applicant: MOTOROLA, INC.

Inventor： KUSHNER, William, M. ,  SRENGER, Edward ,  HARTMAN, Matthew, A.

IPC: G10L15

CPC classification number: G10L15/142

Abstract: In a statistical based speech recognition system, one of the key issues is the selection of the Hidden Markov Model that best matches a given sequence of feature observations. The problem is usually addressed by the calculation of the maximum likelihood, ML, state sequence by means of a Viterbi or other decoder. Noise or inadequate training can produce an ML sequence associated with a Hidden Markov Model other than the correct model. The method of the present invention provides improved robustness by combining the standard ML state sequence score (416) with an additional path core (418) derived from the dynamics of the ML score as a function of time. These two scores, when combined, form a hybrid metric (420) that, when used with the decoder, optimizes selection of the correct Hidden Markov Model (422).

公开(公告)号：WO2006101673A1

公开(公告)日：2006-09-28

申请号：PCT/US2006/006822

申请日：2006-02-27

Applicant: MOTOROLA, INC. ,  ROKUSEK, Daniel, S. ,  KAMBHAMPATI, Kranti, K. ,  NEDELCU, Bogdan, R. ,  SRENGER, Edward

Inventor： ROKUSEK, Daniel, S. ,  KAMBHAMPATI, Kranti, K. ,  NEDELCU, Bogdan, R. ,  SRENGER, Edward

IPC: H04M1/64

CPC classification number: G10L15/22 ,  H04M1/271 ,  H04M1/56 ,  H04M3/4936

Abstract: Assisting a user in dialing a telephone call using voice nametags comprises inputting a telephone number with text. A voice nametag from the text is automatically created for each telephone number using grapheme-to-phoneme conversion. Upon initiation of dialing, a spoken phrase is entered and compared to the stored voice nametags. A confidence level score of a match between the spoken phrase and the representations of the stored voice nametags against at least one threshold is determined. The stored voice nametag with the best match to the spoken phrase is selected, and feedback is provided to the user dependent upon the confidence level of the match, which can include automatically dialing the call. An audio feedback tag may be generated and stored based on the recognition result passing a confidence threshold criterion. Further steps are provided for improving the audio quality of the stored nametag based on signal-to-noise ratio.

Abstract translation: 协助用户使用语音标签拨号电话包括用文本输入电话号码。 使用字母到音素转换，为每个电话号码自动创建文本中的语音名称。 在拨号开始时，输入一个口语短语，并将其与存储的语音名称进行比较。 确定口头短语与所存储的语音名称对应于至少一个阈值的表示之间的匹配的置信水平分数。 选择与口语短语最佳匹配的所存储的语音名称，并且根据匹配的置信水平提供给用户的反馈，其可以包括自动拨打呼叫。 可以基于通过置信阈值标准的识别结果来生成和存储音频反馈标签。 提供了进一步的步骤，用于基于信噪比改善存储的名称的音频质量。

公开(公告)号：WO2006101649A3

公开(公告)日：2006-09-28

申请号：PCT/US2006/006053

申请日：2006-02-21

Applicant: MOTOROLA, INC. ,  SRENGER, Edward ,  ROKUSEK, Daniel, S. ,  WEIRICH, Kevin, L.

Inventor： SRENGER, Edward ,  ROKUSEK, Daniel, S. ,  WEIRICH, Kevin, L.

IPC: G06F9/00

Abstract: A method and apparatus for adapting a help menu on a user interface, utilizing an input method such as a speech recognition system, for increased efficiency. A list of menu items is presented on the user interface including an optional menu item to reinstate any previously removed menu items. A user selects an item from the menu, such as a help menu, which can then be removed from the list of menu items in accordance with predetermined criteria. The criteria can include how many times the menu item has been accessed and when. In this way, help menu items that are familiar to a user are removed to provide an abbreviated help menu which is more efficient and less frustrating to a user, particularly in a busy and distracting environment such as a vehicle.

公开(公告)号：WO1996030895A1

公开(公告)日：1996-10-03

申请号：PCT/US1996000968

申请日：1996-01-29

Applicant: MOTOROLA INC.

Inventor： MOTOROLA INC. ,  KUSHNER, William, M. ,  SRENGER, Edward ,  HARTMAN, Matthew, A.

IPC: G10L09/00

CPC classification number: G10L15/142

Abstract: In a statistical based speech recognition system, one of the key issues is the selection of the Hidden Markov Model that best matches a given sequence of feature observations. The problem is usually addressed by the calculation of the maximum likelihood, ML, state sequence by means of a Viterbi or other decoder. Noise or inadequate training can produce an ML sequence associated with a Hidden Markov Model other than the correct model. The method of the present invention provides improved robustness by combining the standard ML state sequence score (416) with an additional path core (418) derived from the dynamics of the ML score as a function of time. These two scores, when combined, form a hybrid metric (420) that, when used with the decoder, optimizes selection of the correct Hidden Markov Model (422).

Abstract translation: 在基于统计的语音识别系统中，关键问题之一是选择与给定的特征观测序列最匹配的隐马尔可夫模型。 通常通过维特比或其他解码器的最大似然度ML，状态序列的计算来解决该问题。 噪音或训练不足可产生与正确模型以外的隐马尔可夫模型相关的ML序列。 本发明的方法通过将标准ML状态序列分数（416）与作为时间的函数的ML得分的动力学导出的附加路径核心（418）组合来提供改进的鲁棒性。 当组合时，这两个分数形成混合度量（420），当与解码器一起使用时，优化选择正确的隐马尔可夫模型（422）。