公开(公告)号：HK1225504B

公开(公告)日：2017-09-08

申请号：HK16113666

申请日：2016-11-30

Applicant: APPLE INC

Inventor： HENTON CAROLINE ,  NAIK DEVANG

IPC: G06F40/00

公开(公告)号：ES2385029T3

公开(公告)日：2012-07-17

申请号：ES02737515

申请日：2002-06-11

Applicant: APPLE INC

Inventor： BELLEGARDA JEROME R ,  NAIK DEVANG ,  SILVERMAN KIM E A

IPC: G06Q10/00 ,  G06Q10/10 ,  H04L12/58

Abstract: Un procedimiento implementado por ordenador para filtrar mensajes que comprende:determinar (315) una primera ancla semántica (120) que representa un primer vector en un espacio vectorialsemántico correspondiente a un primer grupo de mensajes y una segunda ancla semántica (125) querepresenta un segundo vector en el espacio vectorial semántico correspondiente a un segundo grupo demensajes, en el que el primer vector y el segundo vector fueron derivados a partir de un cuerpo deentrenamiento que comprendía el primer grupo de mensajes y el segundo grupo de mensajes, y en el primergrupo de mensajes y el segundo grupo de mensajes son diferentes;determinar (325), en el espacio vectorial semántico, una representación matemática como un tercer vectorcorrespondiente a un mensaje entrante que tiene texto reconocido por máquina;comparar (330) la representación matemática correspondiente al mensaje entrante con la primera anclasemántica y la segunda ancla semántica para obtener un primer valor de comparación y un segundo valor decomparación; yfiltrar el mensaje entrante clasificando el mensaje entrante entre el primer y segundo grupos en base al primervalor de comparación y el segundo valor de comparación.

公开(公告)号：AU2015261693B2

公开(公告)日：2017-07-20

申请号：AU2015261693

申请日：2015-11-27

Applicant: APPLE INC

Inventor： HENTON CAROLINE ,  NAIK DEVANG

IPC: G10L15/00 ,  G06F40/00

Abstract: Systems and processes for disambiguating heteronyms in speech synthesis are provided. In one example process, a speech input containing a heteronym can be received from a user. The speech input can be processed using an automatic speech recognition system to determine a phonemic string corresponding to the heteronym as pronounced by the user in the speech input. A correct pronunciation of the heteronym can be determined based on at least one of the phonemic string or using an n-gram language model of the automatic speech recognition system. A dialogue response to the speech input can be generated where the dialogue response can include the heteronym. The dialogue response can be outputted as a speech output. The heteronym in the dialogue response can be pronounced in the speech output according to the correct pronunciation. ( ~(D Z1 _ _ __co_ _f c-z 0o col _n Q)0,c ) ro73 0 .) 0 0 Cf) 02 C)= -i;

公开(公告)号：AT551670T

公开(公告)日：2012-04-15

申请号：AT02737515

申请日：2002-06-11

Applicant: APPLE INC

Inventor： BELLEGARDA JEROME ,  NAIK DEVANG ,  SILVERMAN KIM

IPC: G06Q10/00 ,  G06Q10/10 ,  H04L12/58

Abstract: A method and apparatus for filtering messages comprising determining a first semantic anchor corresponding to a first group of messages, for example, legitimate messages and a second semantic anchor corresponding to a second group of messages, for example, unsolicited messages. Determining a vector corresponding to an incoming message; comparing the vector corresponding to the incoming message with at least one of the first semantic anchor and the second semantic anchor to obtain a first comparison value and a second comparison value; and filtering the incoming message based on the first comparison value and the second comparison value.

公开(公告)号：AU2015261693A1

公开(公告)日：2016-06-23

申请号：AU2015261693

申请日：2015-11-27

Applicant: APPLE INC

Inventor： HENTON CAROLINE ,  NAIK DEVANG

IPC: G10L15/00 ,  G06F40/00

Abstract: Systems and processes for disambiguating heteronyms in speech synthesis are provided. In one example process, a speech input containing a heteronym can be received from a user. The speech input can be processed using an automatic speech recognition system to determine a phonemic string corresponding to the heteronym as pronounced by the user in the speech input. A correct pronunciation of the heteronym can be determined based on at least one of the phonemic string or using an n-gram language model of the automatic speech recognition system. A dialogue response to the speech input can be generated where the dialogue response can include the heteronym. The dialogue response can be outputted as a speech output. The heteronym in the dialogue response can be pronounced in the speech output according to the correct pronunciation. ( ~(D Z1 _ _ __co_ _f c-z 0o col _n Q)0,c ) ro73 0 .) 0 0 Cf) 02 C)= -i;

公开(公告)号：HK1060920A1

公开(公告)日：2004-08-27

申请号：HK04103883

申请日：2004-05-31

Applicant: APPLE INC

Inventor： BELLEGARDA JEROME R ,  NAIK DEVANG ,  SILVERMAN KIM E A

IPC: G06Q10/10 ,  H04L20060101 ,  H04L12/58

Abstract: A method and apparatus for filtering messages comprising determining a first semantic anchor corresponding to a first group of messages, for example, legitimate messages and a second semantic anchor corresponding to a second group of messages, for example, unsolicited messages. Determining a vector corresponding to an incoming message; comparing the vector corresponding to the incoming message with at least one of the first semantic anchor and the second semantic anchor to obtain a first comparison value and a second comparison value; and filtering the incoming message based on the first comparison value and the second comparison value.

公开(公告)号：WO2010036486A3

公开(公告)日：2010-05-27

申请号：PCT/US2009055580

申请日：2009-09-01

Applicant: APPLE INC ,  ROGERS MATTHEW ,  SILVERMAN KIM ,  NAIK DEVANG ,  LENZO KEVIN ,  ROTTLER BENJAMIN

Inventor： ROGERS MATTHEW ,  SILVERMAN KIM ,  NAIK DEVANG ,  LENZO KEVIN ,  ROTTLER BENJAMIN

IPC: G10L13/08 ,  G06F17/27 ,  G06F17/28

CPC classification number: G10L13/08 ,  G06F17/275

Abstract: Algorithms for synthesizing speech used to identify media assets are provided. Speech may be selectively synthesized from text strings associated with media assets. A text string may be normalized and its native language determined for obtaining a target phoneme for providing human- sounding speech in a language (e.g., dialect or accent) that is familiar to a user. The algorithms may be implemented on a system including several dedicated render engines. The system may be part of a back end coupled to a front end including storage for media assets and associated synthesized speech, and a request processor for receiving and processing requests that result in providing the synthesized speech. The front end may communicate media assets and associated synthesized speech content over a network to host devices coupled to portable electronic devices on which the media assets and synthesized speech are played back.

Abstract translation: 提供了用于合成用于识别媒体资产的语音的算法。 可以从与媒体资产相关联的文本串中选择性地合成语音。 文本字符串可以被归一化，并且其母语被确定为获得目标音素，以便以用户熟悉的语言（例如方言或重音）提供人声音语音。 算法可以在包括几个专用渲染引擎的系统上实现。 该系统可以是耦合到前端的后端的一部分，包括用于媒体资产和相关联的合成语音的存储器，以及用于接收和处理导致提供合成语音的请求的请求处理器。 前端可以通过网络将媒体资产和相关联的合成语音内容通信到主机耦合到其上播放媒体资产和合成语音的便携式电子设备的设备。