WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT

Embodiments of this application disclose a speech wakeup method and apparatus, a device, a storage medium, and a program product, and pertain to the field of speech recognition technologies. In embodiments of this application, a bone conduction microphone collects a bone conduction signal for speech...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SHENG, Jinhui, LI, Xiaojian, JIANG, Wei, LANG, Yue
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
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 SHENG, Jinhui
LI, Xiaojian
JIANG, Wei
LANG, Yue
description Embodiments of this application disclose a speech wakeup method and apparatus, a device, a storage medium, and a program product, and pertain to the field of speech recognition technologies. In embodiments of this application, a bone conduction microphone collects a bone conduction signal for speech detection, to ensure low power consumption. In addition, it is considered that a delay of speech detection may cause losing of a header of a collected air conduction signal, and consequently, complete information of a command word input by a sound source is not included. However, the bone conduction signal collected by the bone conduction microphone includes information about the command word input by the sound source, that is, the bone conduction signal does not lose a header. Therefore, this solution detects a wakeup word based on the bone conduction signal. In this way, recognition accuracy of a wakeup word is high, and accuracy of speech wakeup is high.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4379712A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4379712A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4379712A13</originalsourceid><addsrcrecordid>eNrjZPAPd_R21fX30w3z93R2VfB1DfHwd1Fw9APigADHIMeQ0GAdBRfXMKCkjkJwiH-QoztIlYtnqK8OWFlAkL97kKMviHYJdQ7hYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgEmxuaW5oZGjobGRCgBAKrxLfA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT</title><source>esp@cenet</source><creator>SHENG, Jinhui ; LI, Xiaojian ; JIANG, Wei ; LANG, Yue</creator><creatorcontrib>SHENG, Jinhui ; LI, Xiaojian ; JIANG, Wei ; LANG, Yue</creatorcontrib><description>Embodiments of this application disclose a speech wakeup method and apparatus, a device, a storage medium, and a program product, and pertain to the field of speech recognition technologies. In embodiments of this application, a bone conduction microphone collects a bone conduction signal for speech detection, to ensure low power consumption. In addition, it is considered that a delay of speech detection may cause losing of a header of a collected air conduction signal, and consequently, complete information of a command word input by a sound source is not included. However, the bone conduction signal collected by the bone conduction microphone includes information about the command word input by the sound source, that is, the bone conduction signal does not lose a header. Therefore, this solution detects a wakeup word based on the bone conduction signal. In this way, recognition accuracy of a wakeup word is high, and accuracy of speech wakeup is high.</description><language>eng ; fre ; ger</language><subject>ACOUSTICS ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240605&amp;DB=EPODOC&amp;CC=EP&amp;NR=4379712A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240605&amp;DB=EPODOC&amp;CC=EP&amp;NR=4379712A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SHENG, Jinhui</creatorcontrib><creatorcontrib>LI, Xiaojian</creatorcontrib><creatorcontrib>JIANG, Wei</creatorcontrib><creatorcontrib>LANG, Yue</creatorcontrib><title>WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT</title><description>Embodiments of this application disclose a speech wakeup method and apparatus, a device, a storage medium, and a program product, and pertain to the field of speech recognition technologies. In embodiments of this application, a bone conduction microphone collects a bone conduction signal for speech detection, to ensure low power consumption. In addition, it is considered that a delay of speech detection may cause losing of a header of a collected air conduction signal, and consequently, complete information of a command word input by a sound source is not included. However, the bone conduction signal collected by the bone conduction microphone includes information about the command word input by the sound source, that is, the bone conduction signal does not lose a header. Therefore, this solution detects a wakeup word based on the bone conduction signal. In this way, recognition accuracy of a wakeup word is high, and accuracy of speech wakeup is high.</description><subject>ACOUSTICS</subject><subject>MUSICAL INSTRUMENTS</subject><subject>PHYSICS</subject><subject>SPEECH ANALYSIS OR SYNTHESIS</subject><subject>SPEECH OR AUDIO CODING OR DECODING</subject><subject>SPEECH OR VOICE PROCESSING</subject><subject>SPEECH RECOGNITION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPAPd_R21fX30w3z93R2VfB1DfHwd1Fw9APigADHIMeQ0GAdBRfXMKCkjkJwiH-QoztIlYtnqK8OWFlAkL97kKMviHYJdQ7hYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgEmxuaW5oZGjobGRCgBAKrxLfA</recordid><startdate>20240605</startdate><enddate>20240605</enddate><creator>SHENG, Jinhui</creator><creator>LI, Xiaojian</creator><creator>JIANG, Wei</creator><creator>LANG, Yue</creator><scope>EVB</scope></search><sort><creationdate>20240605</creationdate><title>WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT</title><author>SHENG, Jinhui ; LI, Xiaojian ; JIANG, Wei ; LANG, Yue</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4379712A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>ACOUSTICS</topic><topic>MUSICAL INSTRUMENTS</topic><topic>PHYSICS</topic><topic>SPEECH ANALYSIS OR SYNTHESIS</topic><topic>SPEECH OR AUDIO CODING OR DECODING</topic><topic>SPEECH OR VOICE PROCESSING</topic><topic>SPEECH RECOGNITION</topic><toplevel>online_resources</toplevel><creatorcontrib>SHENG, Jinhui</creatorcontrib><creatorcontrib>LI, Xiaojian</creatorcontrib><creatorcontrib>JIANG, Wei</creatorcontrib><creatorcontrib>LANG, Yue</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SHENG, Jinhui</au><au>LI, Xiaojian</au><au>JIANG, Wei</au><au>LANG, Yue</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT</title><date>2024-06-05</date><risdate>2024</risdate><abstract>Embodiments of this application disclose a speech wakeup method and apparatus, a device, a storage medium, and a program product, and pertain to the field of speech recognition technologies. In embodiments of this application, a bone conduction microphone collects a bone conduction signal for speech detection, to ensure low power consumption. In addition, it is considered that a delay of speech detection may cause losing of a header of a collected air conduction signal, and consequently, complete information of a command word input by a sound source is not included. However, the bone conduction signal collected by the bone conduction microphone includes information about the command word input by the sound source, that is, the bone conduction signal does not lose a header. Therefore, this solution detects a wakeup word based on the bone conduction signal. In this way, recognition accuracy of a wakeup word is high, and accuracy of speech wakeup is high.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4379712A1
source esp@cenet
subjects ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
title WAKE-ON-VOICE METHOD AND APPARATUS, DEVICE, STORAGE MEDIUM, AND PROGRAM PRODUCT
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T03%3A37%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=SHENG,%20Jinhui&rft.date=2024-06-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4379712A1%3C/epo_EVB%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