公开(公告)号：AU2016203762A1

公开(公告)日：2016-06-23

申请号：AU2016203762

申请日：2016-06-06

Applicant: APPLE INC

Inventor： NAIK DEVANG K

IPC: G10L13/08

Abstract: Systems and methods are provided for associating a phonetic pronunciation with a name by receiving the name, mapping the name to a plurality of monosyllabic components that are combinable to construct the phonetic pronunciation of the name, receiving a user input to select 5 one or more of the plurality, and combining the selected one or more of the plurality of monosyllabic components to construct the phonetic pronunciation of the name.

公开(公告)号：AU2011289500A1

公开(公告)日：2013-02-28

申请号：AU2011289500

申请日：2011-08-09

Applicant: APPLE INC

Inventor： NAIK DEVANG K ,  TIENE KEVIN

IPC: H04M1/725 ,  H04L29/06 ,  H04N1/00

Abstract: One or more media items can be bound to a voice call using a binding protocol. The binding protocol allows call participants to more easily transfer media items to other call participants using one or more user interfaces. A call participant can initiate a media transfer by selecting the media and a communication modality for transferring the media. The binding protocol can be active or lazy. In lazy binding, the call participant can select the desired media for transfer before the voice call is established, and subsequently mark the media for binding with the voice call. In active binding, the call participant can select and transfer the desired media item during the voice call, and the media item is automatically bound to the voice call. The media item can be transferred using a user-selected communication modality over an independent data communication channel.

公开(公告)号：AU2015277773B2

公开(公告)日：2017-11-02

申请号：AU2015277773

申请日：2015-05-06

Applicant: APPLE INC

Inventor： NAIK DEVANG K ,  KAJAREKAR SACHIN S

IPC: G10L25/78 ,  G10L17/00

Abstract: Systems and processes for robust end-pointing of speech signals using speaker recognition are provided. In one example process, a stream of audio having a spoken user request can be received. A first likelihood that the stream of audio includes user speech can be determined. A second likelihood that the stream of audio includes user speech spoken by an authorized user can be determined. A start-point or an end-point of the spoken user request can be determined based at least in part on the first likelihood and the second likelihood.

公开(公告)号：AU2017100208A4

公开(公告)日：2017-03-23

申请号：AU2017100208

申请日：2017-02-21

Applicant: APPLE INC

Inventor： NAIK DEVANG K ,  MOHAMED ALI S ,  CHEN HONG M

IPC: G10L15/06 ,  G10L15/187

Abstract: Systems and processes for generating a shared pronunciation lexicon and using the shared pronunciation lexicon to interpret spoken user inputs received by a virtual assistant are provided. In one example, the process can include receiving pronunciations for words or named entities from multiple users. The pronunciations can be tagged with context tags and stored in the shared pronunciation lexicon. The shared pronunciation lexicon can then be used to interpret a spoken user input received by a user device by determining a relevant subset of the shared pronunciation lexicon based on contextual information associated with the user device and performing speech-to-text conversion on the spoken user input using the determined subset of the shared pronunciation lexicon.

公开(公告)号：MX2013001676A

公开(公告)日：2013-03-25

申请号：MX2013001676

申请日：2011-08-09

Applicant: APPLE INC

Inventor： NAIK DEVANG K ,  TIENE KEVIN

IPC: H04M1/725 ,  H04L29/06 ,  H04N1/00

Abstract: Uno o más elementos multimedia pueden enlazarse a una llamada de voz al utilizar un protocolo de enlace. El protocolo de enlace permite que los participantes de la llamada transfieran más fácilmente elementos multimedia a otros participantes de la llamada al utilizar una o más interfaces de usuario. Una participante de la llamada puede iniciar una transferencia multimedia al seleccionar el contenido multimedia y una modalidad de comunicación para transferir el contenido multimedia. El protocolo de enlace puede ser activo o lento. En el enlace lento, el participante de la llamada puede seleccionar el contenido multimedia deseado para transferir antes de que la llamada de voz se establezca, y de manera subsecuente marcar el contenido multimedia para el enlace con la llamada de voz. En el enlace activo, el participante de la llamada puede seleccionar y transferir el elemento multimedia deseado durante !a llamada de voz, y el elemento multimedia se enlaza automáticamente a la llamada de voz. El elemento multimedia puede transferirse al utilizar una modalidad de comunicación seleccionada por el usuario a través de un canal de comunicación de datos independiente.

公开(公告)号：WO2014197334A3

公开(公告)日：2015-01-29

申请号：PCT/US2014040393

申请日：2014-05-30

Applicant: APPLE INC ,  NAIK DEVANG K ,  WEINER LIAM ,  BINDER JUSTIN G ,  SRISUWANANUKORN CHARLES ,  EVERMANN GUNNAR ,  WILLIAMS SHAUN ,  CHEN HONG ,  NAPOLITANO LIA T

Inventor： NAIK DEVANG K ,  WEINER LIAM ,  BINDER JUSTIN G ,  SRISUWANANUKORN CHARLES ,  EVERMANN GUNNAR ,  WILLIAMS SHAUN ,  CHEN HONG ,  NAPOLITANO LIA T ,  GRUBER THOMAS R

IPC: G10L13/00 ,  G10L13/04 ,  G10L15/22 ,  G10L15/26

CPC classification number: G10L13/027 ,  G10L13/04 ,  G10L13/08 ,  G10L15/063 ,  G10L15/22 ,  G10L15/26 ,  G10L15/265 ,  G10L2015/0631 ,  G10L2015/0638

Abstract: The method is performed at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors. A first speech input including at least one word is received. A first phonetic representation of the at least one word is determined, the first phonetic representation comprising a first set of phonemes selected from a speech recognition phonetic alphabet. The first set of phonemes is mapped to a second set of phonemes to generate a second phonetic representation, where the second set of phonemes is selected from a speech synthesis phonetic alphabet. The second phonetic representation is stored in association with a text string corresponding to the at least one word.

Abstract translation: 该方法在具有一个或多个处理器的电子设备中执行，存储器存储一个或多个程序以供一个或多个处理器执行。 接收包括至少一个字的第一语音输入。 确定所述至少一个单词的第一语音表示，所述第一语音表示包括从语音识别语音字母表中选择的第一组音素。 将第一组音素映射到第二组音素以产生第二语音表示，其中从语音合成语音字母表中选择第二组音素。 第二语音表示与对应于至少一个单词的文本串相关联地存储。

公开(公告)号：WO2013130878A3

公开(公告)日：2013-11-07

申请号：PCT/US2013028412

申请日：2013-02-28

Applicant: APPLE INC

Inventor： NAIK DEVANG K

IPC: G10L13/08

CPC classification number: G10L13/08 ,  G10L13/086 ,  G10L15/187

Abstract: Systems and methods are provided for associating a phonetic pronunciation with a name by receiving the name, mapping the name to a plurality of monosyllabic components that are combinable to construct the phonetic pronunciation of the name, receiving a user input to select one or more of the plurality, and combining the selected one or more of the plurality of monosyllabic components to construct the phonetic pronunciation of the name.

Abstract translation: 提供了系统和方法，用于通过接收名称来将语音发音与名称相关联，将名称映射到可组合以构建名称的语音发音的多个单音节组件，接收用户输入以选择一个或多个 多个，并且组合所选择的一个或多个单音节组件以构建该名称的语音发音。

公开(公告)号：EP2815397B1

公开(公告)日：2017-05-03

申请号：EP13709284

申请日：2013-02-28

Applicant: APPLE INC

Inventor： NAIK DEVANG K

IPC: G10L13/08

CPC classification number: G10L13/08 ,  G10L13/086 ,  G10L15/187

Abstract: A method comprising: providing a plurality of pronunciation guessers, each of the plurality of pronunciation guessers being associated with a respective phonetic alphabet of a language or a locale; determining a user language or a user locale; associating a first phonetic alphabet with the user language or the user locale; receiving at each pronunciation guesser a representation of a name; guessing, at each pronunciation guesser, a phonetic pronunciation of one or more components of the name; mapping the phonetic pronunciation of the one or more components of the name guessed by each of the plurality of pronunciation guessers to the first phonetic alphabet to generate a list of guessed pronunciations; receiving an audio pronunciation of the name; and selecting a combination of components from the list of guessed pronunciations that, when pronounced, substantially matches the audio pronunciation of the name.

Abstract translation: 1。一种方法，包括：提供多个发音猜测器，所述多个发音猜测器中的每一个与语言或场所的相应语音字母表相关联; 确定用户语言或用户区域; 将第一语音字母与用户语言或用户语言相关联; 在每个发音猜测者处接收名称的表示; 猜测，在每个发音guesser，这个名字的一个或多个组件的语音发音; 将由所述多个发音猜测器中的每一个猜测的名称的一个或多个分量的语音发音映射到第一语音字母表以生成猜测发音的列表; 接收名称的音频发音; 并且从被猜测的发音列表中选择组成部分的组合，当发音时，其基本上匹配该名字的音频发音。