公开(公告)号：US4503528A

公开(公告)日：1985-03-05

申请号：US354045

申请日：1982-03-02

申请人： Tadao Nojiri ,  Kenji Kanamaru ,  Masahiro Matsuyama ,  Takayoshi Nishikawa ,  Yoji Ito

发明人： Tadao Nojiri ,  Kenji Kanamaru ,  Masahiro Matsuyama ,  Takayoshi Nishikawa ,  Yoji Ito

IPC分类号： B60H1/00 ,  B60R16/02 ,  B60R16/037 ,  G05B24/00 ,  G05B24/02 ,  G10L13/00 ,  H03G1/02 ,  H03J1/02 ,  H04Q9/00 ,  B60Q1/00 ,  G10L1/04 ,  H04B1/46

CPC分类号： B60R16/0373 ,  B60H1/00757 ,  H03G1/02 ,  H03J1/025

摘要： A demand for a change in the operating condition of at least one of a plurality of vehicle mounted devices is issued by means of a single push button switch attached to the center of the steering wheel. When the vehicle occupant intends to manipulate a device such as a radio, stereo unit or an air conditioner, he depresses the switch to supply a microcomputer with a demand signal. The microcomputer produces an instruction signal with which a sound synthesizer produces sequential vocal announcements which are emitted via a speaker. The occupant depresses the switch again within a predetermined period of time after the emission of a vocal announcement naming a device intended to control so that the sound synthesizer now provides various manipulative information relating to the available manipulations of the selected device. The driver depresses the switch to issue responsive instructions in response to an announcement of desired manipulation. The microcomputer thus operates to produce necessary control signals which are fed to a corresponding control unit of the selected device. A sound recognizer may be used in place of or together with the switch to detect the demand and responsive instructions from the driver.

摘要翻译： 通过安装在方向盘的中心的单个按钮开关来发出对多个车载装置中的至少一个的操作状态的改变的要求。 当车辆乘员想要操纵诸如无线电，立体声单元或空调的设备时，他按下开关以向需要信号的微型计算机供电。 微型计算机产生指令信号，声音合成器通过该信号产生通过扬声器发出的连续的声音通知。 乘客在发出命名要控制的设备的声音通知之后的预定时间段内再次按下开关，使得声音合成器现在提供与所选择的设备的可用操作有关的各种操纵信息。 驾驶员按下开关以响应于期望的操纵的公告发出响应指令。 因此，微计算机操作以产生必需的控制信号，该控制信号被馈送到所选设备的相应控制单元。 可以使用声音识别器代替或与开关一起检测来自驾驶员的需求和响应指令。

公开(公告)号：US3896266A

公开(公告)日：1975-07-22

申请号：US25924872

申请日：1972-06-02

申请人： WATERBURY NELSON J

发明人： WATERBURY NELSON J

IPC分类号： G11B5/80 ,  B42D15/10 ,  G07C9/00 ,  G07F7/10 ,  G10L17/00 ,  G10L1/04

CPC分类号： G07F7/10 ,  G06Q20/347 ,  G07C9/00087 ,  G07F7/1075 ,  G10L17/00

摘要： A security card (which may be a credit card) according to the invention has recorded on it data identifying a personal and noncounterfeitable attribute, such as the voice characteristics, of the authorised holder of the card. A card utilisation system according to the invention provides means for comparing the attribute as recorded by these data with the corresponding attribute of the person wishing to use the card, thereby substantially eliminating the possibility of unauthorised use of the card. The utilisation system, when applied to credit card utilisation, preferably includes document facsimile transmission, whereby, for example, a credit card user obtaining credit remotely can be provided with a facsimile copy of the usual credit sale document, which facsimile copy he signs before transmitting another facsimile copy, this time of the signed first copy, to provide the remote credit issuing location with his authentication of the transaction. Preferably, also, the system includes provision for television communication between credit card holders and the credit-giving locations, whereby, for example, a remote would-be purchaster can be shown goods in which he is interested. The system is also adapted to provide for credit card payment in, for example, pay television distribution systems and for remote purchase of theatre and airline tickets and of services such as the supply of information from computerised information systems and computerised translation services. Individual human voices embody characteristics which are unique and identifiable. A credit card can, therefore, be equipped with a voiceprint-cipher, which can be used to corroborate authorised possession by the card-holder. Contourlines or numerically coded representations can be used to embody the voice-print information on the credit card, and electronic comparators can be used for automatic verification of identity. The voice cipher can be combined with a charge account code cipher, to provide further protection of the integrity of a credit card.

公开(公告)号：US3821472A

公开(公告)日：1974-06-28

申请号：US22929072

申请日：1972-02-25

申请人： THRESHOLD TECH

发明人： HERSCHER M ,  MARTIN T

IPC分类号： G10L15/00 ,  G10L1/04

CPC分类号： G10L15/00

摘要： An apparatus that receives ambient sounds and recognizes the occurrence of coughs to the exclusion of other sounds. Means are provided for translating the received sounds into a plurality of spectral component signals. A feature signal generating means is provided for sensing the presence of properties of the spectral component signals that are characteristic of coughs and for generating a feature signal for each property found to be present. An occurrence decision means, responsive to the feature signals, generates an occurrence indication upon receiving a predetermined combination of feature signals. In a preferred embodiment of the invention, the occurrence decision means is programmable to the cough of a particular individual.

公开(公告)号：US3549806A

公开(公告)日：1970-12-22

申请号：US3549806D

申请日：1967-05-05

申请人： GEN ELECTRIC

发明人： WOOD DAVID E

IPC分类号： G10L25/93 ,  G10L1/04

CPC分类号： G10L25/93

公开(公告)号：US4596031A

公开(公告)日：1986-06-17

申请号：US451937

申请日：1982-12-21

申请人： Mitsuhiro Hakaridani ,  Yoshiki Nishioka ,  Hiroyuki Iwahashi

发明人： Mitsuhiro Hakaridani ,  Yoshiki Nishioka ,  Hiroyuki Iwahashi

IPC分类号： G10L11/00 ,  G10L15/00 ,  G10L15/08 ,  G10L15/28 ,  G10L1/04

CPC分类号： G10L15/00

摘要： In a speech recognition system, similarity calculations between speech feature patterns are reduced by stopping similarity calculations for any one reference pattern when a frame in the pattern fails to exceed a corresponding similarity threshold.

摘要翻译： 在语音识别系统中，当模式中的帧不能超过对应的相似性阈值时，通过停止任何一个参考模式的相似度计算来减少语音特征模式之间的相似度计算。

公开(公告)号：US4084245A

公开(公告)日：1978-04-11

申请号：US714103

申请日：1976-08-13

申请人： Ernst Bunge

发明人： Ernst Bunge

IPC分类号： G10L15/10 ,  G01H3/00 ,  G01H3/08 ,  G01R23/165 ,  G01R23/167 ,  G10L15/02 ,  G10L1/04

CPC分类号： G01R23/165

摘要： An arrangement for signal analysis in which the function to be examined is split into its spectral components in a filter bank. The signal values of the individual components are successively applied to a comparison device and to the input of a store. The output of the store feeds the other input of the comparison device which generates a signal whenever the instantaneous signal values of all spectral components correspond to the stored, corresponding signal values, within predetermined tolerance limits. The successful comparison of each time a pair of signal values is counted for all spectral components, and the output signal is generated only if a predetermined counter position is reached. As a result, complete correspondence is not required. An additional pulse generator can also generate pulses for given spectral components which correspond to a successful comparison. The directly successive pulses of the comparison device are counted, and in the case of a negative overall comparison this counter position is transferred to a histogram-forming device which separately counts the numbers of the various counter positions.

公开(公告)号：US3925616A

公开(公告)日：1975-12-09

申请号：US46560474

申请日：1974-04-30

申请人： BELL TELEPHONE LABOR INC

发明人： SONDHI MAN MOHAN

IPC分类号： A61B1/267 ,  A61B7/00 ,  G10L1/04

CPC分类号： A61B7/00 ,  A61B1/2673

摘要： Apparatus, for determining the glottal waveform of a subject, is disclosed which comprises a hard-walled, uniform, cylindrical, acoustic waveguide having a cross-sectional area commensurate with that of the vocal tract of the subject. The waveguide is terminated at one end to substantially reduce acoustic wave reflections. A microphone is positioned within the wall of the waveguide to detect and convey to suitable instrumentation the glottal waveform of the subject.

摘要翻译： 公开了用于确定对象的声门波形的装置，其包括硬壁均匀的圆柱形声波导，其横截面面积与对象的声道的横截面面积相当。 波导在一端被终止，从而大大减少声波反射。 麦克风定位在波导的壁内，以检测并传送到合适的仪器，使对象的声门波形。

公开(公告)号：US3870818A

公开(公告)日：1975-03-11

申请号：US39129773

申请日：1973-08-24

申请人： SPEECH TECHNOLOGY CORP

发明人： BARTON WILLIAM A ,  STORK JOHN E

IPC分类号： B60R16/02 ,  B60R16/037 ,  G10L1/04

CPC分类号： B60R16/0373

摘要： A voice response device similar to an annuciator includes comprising individual circuits each capable upon triggering of generating speech synthesizing signals corresponding to a given word or phrase. Digital code groups represent the permanently stored words or phrases. A particular code group is generated and applied to the storage unit to reproduce the corresponding message only if a given condition occurs. The voice response system is ideally suited to automobiles wherein a condition such as an unfastened seat belt will automatically generate a digital code group which when applied to the storage unit results in an audible formation of a message such as ''''fasten seat belt''''.

摘要翻译： 类似于一个通告器的话音响应装置包括各自的电路，每个电路能够触发产生对应给定单词或短语的语音合成信号。 数字代码组表示永久存储的单词或短语。 生成特定代码组并将其应用于存储单元，以仅在给定条件发生时再现相应的消息。 声音响应系统非常适用于汽车，其中诸如松开安全带的状况将自动生成数字代码组，当应用于存储单元时，可以形成诸如“紧固安全带”的消息的可听见的形式。

公开(公告)号：US3742146A

公开(公告)日：1973-06-26

申请号：US3742146D

申请日：1970-10-20

申请人： NAT RES DEV

发明人： NEWMAN E ,  PAY B ,  MANNING D

IPC分类号： G10L19/02 ,  G10L25/00 ,  G10L1/04

CPC分类号： G10L25/00 ,  G10L19/02

摘要： The recognition of signals having specific periods is described particularly in relation to recognising vowels. Characteristic frequencies in vowels are recognised by circuits which delay the input signals for an interval related to a frequency to be recognised, correlate the delayed signals with undelayed input signals and integrate the resultant over a short period comparable with the duration of the vowel sound. The magnitude and sign of the integrated signal indicates whether the required signal is present. In order to deal with speech an incoming signal is first passed to a special form of AGC circuit and then divided into low and high frequency components. The presence of characteristic frequencies in these components is determined by the technique described above, and logic circuits indicate what combinations of frequencies and thus what vowels are present.

摘要翻译： 关于具有特定周期的信号的识别特别涉及识别元音。 元音中的特征频率由延迟输入信号与待识别频率相关的间隔的电路识别，将延迟的信号与未延迟的输入信号相关，并将结果与​​元音的持续时间相比较。 积分信号的幅度和符号表示是否存在所需的信号。 为了处理语音，输入信号首先传递到AGC电路的特殊形式，然后分为低频和高频分量。 这些分量中的特征频率的存在由上述技术确定，并且逻辑电路指示频率的组合以及因此存在什么元音。

公开(公告)号：US3730995A

公开(公告)日：1973-05-01

申请号：US3730995D

申请日：1971-11-16

申请人： BELL TELEPHONE LABOR INC

发明人： MATHEWS M

IPC分类号： G10L11/02 ,  G10L1/04

CPC分类号： G10L25/78

摘要： Voice activated control apparatus selectively connects one of a plurality of microphones to an audio line and inhibits all other microphones from capturing the line while the initial connection is maintained. Each microphone is connected to an associated speech detector and relay. In response to voice signals from a microphone, the associated speech detector activates a relay which connects the microphone to the line and generates a signal which inhibits the other relays. Other users cannot interrupt the present speaker because their relays remain inhibited as long as the speaker continues. The same circuitry can accommodate any number of microphones.

摘要翻译： 语音激活控制装置选择性地将多个麦克风中的一个连接到音频线，并且在维持初始连接时禁止所有其它麦克风捕获该线。 每个麦克风连接到相关的语音检测器和继电器。 响应于来自麦克风的语音信号，相关联的语音检测器激活将麦克风连接到线路并产生抑制其它继电器的信号的继电器。 只要扬声器继续，其他用户不能中断本扬声器，因为它们的继电器保持禁止。 相同的电路可以容纳任何数量的麦克风。