Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods for pronunciation of names

A technology of name and voice, applied in the field of recognition and synthesis of voice, can solve the problems of inability to pronounce the guesser model, the pronunciation of foreign names cannot be correctly guessed, etc.

Active Publication Date: 2017-08-25
APPLE INC
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because some phonetic units are specific to a particular language, the same name may be pronounced differently by different users
Therefore, existing systems are not able to build sufficient pronunciation guessers to model the pronunciation of names from different languages ​​and cultures
In many cases, foreign name pronunciations may not be guessed correctly unless there are clear rules expressed in the guesser

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods for pronunciation of names
  • Systems and methods for pronunciation of names
  • Systems and methods for pronunciation of names

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In various implementations, the present application provides systems, methods, and devices that provide a user interface to efficiently and conveniently configure the phonetic pronunciation of names. In some configurations, the interface uses a processor that implements an application for mapping an arbitrary name from a user's contacts to multiple monosyllabic names to construct the correct pronunciation of the name. The name may first be syllabled into monosyllables that are readily pronounced by the user in the language the transcription is intended for. A syllable can be thought of as a single element of spoken language comprising a single uninterrupted sound formed from vowels, diphthongs, or syllable consonants. The sound may be preceded by, followed by, or surrounded by a consonant or consonants.

[0038] In some configurations, an interface allows users to enter their own monosyllabic words to accurately represent the pronunciation of the name. The interface c...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides systems and methods for associating phonetic pronunciations with names by receiving a name, mapping the name to multiple monosyllabic components of the phonetic pronunciation that can be combined to construct the name, receiving user input to select One or more of the plurality, and combining a selected one or more of the plurality of monosyllabic components to construct a phonetic pronunciation of the name.

Description

technical field [0001] This application relates to recognizing and synthesizing speech, and more particularly, to recognizing and synthesizing the pronunciation of names. Background technique [0002] Name recognition is a particularly difficult aspect of speech recognition. Names may include the names of people, businesses, and other entities. The distribution of names has a long tail. Also, the way a name is pronounced can be subjective and depend on where the name comes from. There may be a small number of very common names, but there are orders of magnitude higher very rare names. For a speech recognition system to recognize a name, a linguist is typically required to transcribe all possible pronunciations in the phonetic alphabet supported by the region or language in which the speech recognition system is deployed. Most existing speech recognition and synthesis systems have at most hundreds or thousands of names, and there may be millions of actual unique names in ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L13/08
CPCG10L13/08G10L13/086G10L15/187G10L15/26
Inventor D·K·奈科
Owner APPLE INC