Apple Inc.

Kim E A Silverman

Jerome Rene Bellegarda

Devang Kalidas Naik

Scott James Forstall

Kevin Tiene

Gregory N Christie

Bertrand Serlet

Steve S Ko

Paul D Marcos

Mallory Paine

John William Scalo

Bruce Arthur

Joshua Matthew Williams

Matthias Neeracher

A method and system for training a user authentication by voice signal are described. In one embodiment, a set of feature vectors are decomposed into speaker-specific recognition units. The speaker-specific recognition units are used to compute distribution values to train the voice signal. In addition, spectral feature vectors are decomposed into speaker-specific characteristic units which are compared to the speaker-specific distribution values. If the speaker-specific characteristic units are within a threshold limit of the speaker-specific distribution values, the speech signal is authenticated.

Fast, language-independent method for user authentication by voice

Apparatus, methods and systems for creating mosaics are described. A method is provided that includes identifying an image for presentation as a mosaic; dividing the identified image into a plurality of tiles; scoring each tile; identifying a matching image from an image dataset using the score for each tile; and rendering the mosaic using the matching images.

Presenting images as mosaics

A method, apparatus, and system, for scanning a first portion of a data to generate a second portion of data is provided. A control parameter relating to a level of detail associated with filtering a first portion of data is received. The filtering of the first portion of data is performed based upon the control parameter. The filtering of the first portion of data includes a rule-based filtering, a context-based filtering, a statistical-based filtering, or a semantic-based filtering. Performing the filtering provides for a reduction of a portion of the first portion of data. A second portion of data that is smaller than the first portion of data is provided based upon the filtering of the first portion of data.

Intelligent document scanning

Systems, apparatus, methods and computer program products are described for producing text-to-speech synthesis with non-speech sounds. In general, some of the pauses or silences that would otherwise be generated in synthesized speech are instead synthesized as non-speech sounds such as breaths. Non-speech sounds can be identified from pre-recorded speech that can include meta-data such as the grammatical and phrasal structure of words and sounds that precede and succeed non-speech sounds. A non-speech sound can be selected for use in synthesized speech based on the words, punctuation, grammatical and phrasal structure of text from which the speech is being synthesized, or other characteristics.

Using non-speech sounds during text-to-speech synthesis

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.

Method and apparatus for filtering email

A method, apparatus, and signal-bearing medium that files data in a destination based on one or more criteria. In various embodiments, the data may be email, email attachments, faxes, telephone messages, downloaded data or programs, audio, video, scanned images, photographs, blocks of text, or other data. In an embodiment, a training mode and an automatic mode are provided. During the training mode, a user is presented with data and a recommended destination, and the user provides feedback that is used to train the criteria. During an automatic mode, the data may be transferred to the destination with or without user confirmation.

Training a computer storage system for automatic filing of data using graphical representations of storage locations

A method and apparatus is provided for generating speech that sounds more natural. Determining whether information in a current sentence is new or previously given is performed based on a semantic relationship between the current sentence and a number of preceding sentences. A word prominence for the synthetic speech to a word in the current sentence is assigned in accordance with the information determination. A speech representative of the current sentence can be generated. In one embodiment, word prominence and latent semantic analysis are used to generate more natural sounding speech. A method for generating speech that sounds more natural may comprise generating synthesized speech having certain word prominence characteristics and applying a semantically-driven word prominence assignment model to specify word prominence consistent with the way humans assign word prominence.

Method and apparatus for predicting word prominence in speech synthesis

A method, apparatus, and signal-bearing medium that filter data based on a criteria. In an embodiment, the criteria may be related to filtering out unwanted or junk input data. In another embodiment, the criteria may be related to filtering based on desired data. In various embodiments, the data may be email, email attachments, faxes, popup windows, telephone messages, downloaded data or programs, image data, or other data. In a embodiment, a training mode and an automatic mode are provided. During the training mode, a user may be presented with data that may be junk, and feedback may be provided that is used to train a junk filter. During an automatic mode, junk data may be removed from view, transferred to a junk box, or highlighted.

Filtering of data

A method and apparatus is provided for generating speech that sounds more natural. In one embodiment, word prominence and latent semantic analysis are used to generate more natural sounding speech. A method for generating speech that sounds more natural may comprise generating synthesized speech having certain word prominence characteristics and applying a semantically-driven word prominence assignment model to specify word prominence consistent with the way humans assign word prominence. A speech representative of a current sentence is generated. The determination is made whether information in the current sentence is new or previously given in accordance with a semantic relationship between the current sentence and a number of preceding sentences. A word prominence is assigned to a word in the current sentence in accordance with the information determination.

Method and apparatus for assigning word prominence to new or previous information in speech synthesis

An extended finite state grammar structure is generated from a finite state grammar. The extended finite state grammar structure includes word subgraphs representing a set of pre-defined word strings for words in the finite state grammar, and a set of all possible word strings for the words. The extended finite state grammar structure can be used to transform audio input into one or more of the word strings.

Extended finite state grammar for speech recognition systems

A method and apparatus to use semantic inference with speech recognition systems includes recognizing at least one spoken word, processing the spoken word using a context-free grammar, deriving an output from the context-free grammar, and translating the output to a predetermined command.

Growing community of inventors

Mountain View, CA, United States of America

Kim E A Silverman