Method and apparatus for predicting word prominence in speech synthesis

Method and apparatus for predicting word prominence in speech synthesis

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 th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bellegarda, Jerome R, Silverman, Kim E. A
Format: Patent
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Bellegarda, Jerome R
Silverman, Kim E. A
description 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.
format Patent
fullrecord <record><control><sourceid>uspatents_EFH</sourceid><recordid>TN_cdi_uspatents_grants_07778819</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>07778819</sourcerecordid><originalsourceid>FETCH-uspatents_grants_077788193</originalsourceid><addsrcrecordid>eNqNijsKAkEMQKexEPUOuYCgWMxai5_Gzl7CTHZnQDMhySLe3hU8gMXj8eDNw_lKXloG5AkRVPTRoG8KopRr8soDvJrmqduzMnEiqAwmRKmAvdkLWbVlmPX4MFr9vAhwOt4Ol_Vogk7sdh8Uv9rEGLtuu9_9sXwAUzY1VA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method and apparatus for predicting word prominence in speech synthesis</title><source>USPTO Issued Patents</source><creator>Bellegarda, Jerome R ; Silverman, Kim E. A</creator><creatorcontrib>Bellegarda, Jerome R ; Silverman, Kim E. A ; Apple Inc</creatorcontrib><description>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.</description><language>eng</language><creationdate>2010</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7778819$$EPDF$$P50$$Guspatents$$Hfree_for_read</linktopdf><link.rule.ids>230,308,780,802,885,64037</link.rule.ids><linktorsrc>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7778819$$EView_record_in_USPTO$$FView_record_in_$$GUSPTO$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Bellegarda, Jerome R</creatorcontrib><creatorcontrib>Silverman, Kim E. A</creatorcontrib><creatorcontrib>Apple Inc</creatorcontrib><title>Method and apparatus for predicting word prominence in speech synthesis</title><description>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.</description><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2010</creationdate><recordtype>patent</recordtype><sourceid>EFH</sourceid><recordid>eNqNijsKAkEMQKexEPUOuYCgWMxai5_Gzl7CTHZnQDMhySLe3hU8gMXj8eDNw_lKXloG5AkRVPTRoG8KopRr8soDvJrmqduzMnEiqAwmRKmAvdkLWbVlmPX4MFr9vAhwOt4Ol_Vogk7sdh8Uv9rEGLtuu9_9sXwAUzY1VA</recordid><startdate>20100817</startdate><enddate>20100817</enddate><creator>Bellegarda, Jerome R</creator><creator>Silverman, Kim E. A</creator><scope>EFH</scope></search><sort><creationdate>20100817</creationdate><title>Method and apparatus for predicting word prominence in speech synthesis</title><author>Bellegarda, Jerome R ; Silverman, Kim E. A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-uspatents_grants_077788193</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2010</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Bellegarda, Jerome R</creatorcontrib><creatorcontrib>Silverman, Kim E. A</creatorcontrib><creatorcontrib>Apple Inc</creatorcontrib><collection>USPTO Issued Patents</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bellegarda, Jerome R</au><au>Silverman, Kim E. A</au><aucorp>Apple Inc</aucorp><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method and apparatus for predicting word prominence in speech synthesis</title><date>2010-08-17</date><risdate>2010</risdate><abstract>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.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_uspatents_grants_07778819
source USPTO Issued Patents
title Method and apparatus for predicting word prominence in speech synthesis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T10%3A55%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-uspatents_EFH&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Bellegarda,%20Jerome%20R&rft.aucorp=Apple%20Inc&rft.date=2010-08-17&rft_id=info:doi/&rft_dat=%3Cuspatents_EFH%3E07778819%3C/uspatents_EFH%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true