Transformer voiceprint spectrum feature enhancement method and system based on weight allocation
The invention discloses a transformer spectrum feature enhancement method and system based on weight allocation. Firstly, acquisition, noise reduction and spectrum analysis of acoustic signals of the transformer are carried out; secondly, defining different frequency bands as an interference section...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| 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 | HE PING HOU ZHUO XU ZIQIANG LI YONG XU HONGHUA YIN LAIBIN WANG LINGYAN CHEN SHOULONG |
| description | The invention discloses a transformer spectrum feature enhancement method and system based on weight allocation. Firstly, acquisition, noise reduction and spectrum analysis of acoustic signals of the transformer are carried out; secondly, defining different frequency bands as an interference section and an effective section according to amplitudes of different frequency components in an actual frequency spectrum, and performing reference weight calculation for different frequency band types; and finally performing enhancement processing on the spectrum features based on a reference weight calculation result, and verifying the effectiveness of the method based on the accuracy of state prediction before and after enhancement. According to the method, information such as frequency component amplitude and frequency bandwidth in the original frequency spectrum of the signal is analyzed and processed to form a method capable of analyzing reference weights of different frequencies according to the actual frequency s |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116884417A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116884417A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116884417A3</originalsourceid><addsrcrecordid>eNqNyjEOwjAMRuEuDAi4gzkAQ0UFXVEFYmJiLyb9SyM1dpS4IG4PAwdgesP35sXtmlhyrykg0VO9Q0xejHKEszQF6sE2JRBkYHEI-GKADdoRS0f5nQ2B7pzRkQq94B-DEY-jOjavsixmPY8Zq18Xxfp0vDbnDaK2yJEdBNY2l7Lc1XVVlfvD9p_nA1-pPlU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Transformer voiceprint spectrum feature enhancement method and system based on weight allocation</title><source>esp@cenet</source><creator>HE PING ; HOU ZHUO ; XU ZIQIANG ; LI YONG ; XU HONGHUA ; YIN LAIBIN ; WANG LINGYAN ; CHEN SHOULONG</creator><creatorcontrib>HE PING ; HOU ZHUO ; XU ZIQIANG ; LI YONG ; XU HONGHUA ; YIN LAIBIN ; WANG LINGYAN ; CHEN SHOULONG</creatorcontrib><description>The invention discloses a transformer spectrum feature enhancement method and system based on weight allocation. Firstly, acquisition, noise reduction and spectrum analysis of acoustic signals of the transformer are carried out; secondly, defining different frequency bands as an interference section and an effective section according to amplitudes of different frequency components in an actual frequency spectrum, and performing reference weight calculation for different frequency band types; and finally performing enhancement processing on the spectrum features based on a reference weight calculation result, and verifying the effectiveness of the method based on the accuracy of state prediction before and after enhancement. According to the method, information such as frequency component amplitude and frequency bandwidth in the original frequency spectrum of the signal is analyzed and processed to form a method capable of analyzing reference weights of different frequencies according to the actual frequency s</description><language>chi ; eng</language><subject>ACOUSTICS ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2023</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&date=20231013&DB=EPODOC&CC=CN&NR=116884417A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231013&DB=EPODOC&CC=CN&NR=116884417A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HE PING</creatorcontrib><creatorcontrib>HOU ZHUO</creatorcontrib><creatorcontrib>XU ZIQIANG</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>XU HONGHUA</creatorcontrib><creatorcontrib>YIN LAIBIN</creatorcontrib><creatorcontrib>WANG LINGYAN</creatorcontrib><creatorcontrib>CHEN SHOULONG</creatorcontrib><title>Transformer voiceprint spectrum feature enhancement method and system based on weight allocation</title><description>The invention discloses a transformer spectrum feature enhancement method and system based on weight allocation. Firstly, acquisition, noise reduction and spectrum analysis of acoustic signals of the transformer are carried out; secondly, defining different frequency bands as an interference section and an effective section according to amplitudes of different frequency components in an actual frequency spectrum, and performing reference weight calculation for different frequency band types; and finally performing enhancement processing on the spectrum features based on a reference weight calculation result, and verifying the effectiveness of the method based on the accuracy of state prediction before and after enhancement. According to the method, information such as frequency component amplitude and frequency bandwidth in the original frequency spectrum of the signal is analyzed and processed to form a method capable of analyzing reference weights of different frequencies according to the actual frequency s</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEOwjAMRuEuDAi4gzkAQ0UFXVEFYmJiLyb9SyM1dpS4IG4PAwdgesP35sXtmlhyrykg0VO9Q0xejHKEszQF6sE2JRBkYHEI-GKADdoRS0f5nQ2B7pzRkQq94B-DEY-jOjavsixmPY8Zq18Xxfp0vDbnDaK2yJEdBNY2l7Lc1XVVlfvD9p_nA1-pPlU</recordid><startdate>20231013</startdate><enddate>20231013</enddate><creator>HE PING</creator><creator>HOU ZHUO</creator><creator>XU ZIQIANG</creator><creator>LI YONG</creator><creator>XU HONGHUA</creator><creator>YIN LAIBIN</creator><creator>WANG LINGYAN</creator><creator>CHEN SHOULONG</creator><scope>EVB</scope></search><sort><creationdate>20231013</creationdate><title>Transformer voiceprint spectrum feature enhancement method and system based on weight allocation</title><author>HE PING ; HOU ZHUO ; XU ZIQIANG ; LI YONG ; XU HONGHUA ; YIN LAIBIN ; WANG LINGYAN ; CHEN SHOULONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116884417A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>HE PING</creatorcontrib><creatorcontrib>HOU ZHUO</creatorcontrib><creatorcontrib>XU ZIQIANG</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>XU HONGHUA</creatorcontrib><creatorcontrib>YIN LAIBIN</creatorcontrib><creatorcontrib>WANG LINGYAN</creatorcontrib><creatorcontrib>CHEN SHOULONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HE PING</au><au>HOU ZHUO</au><au>XU ZIQIANG</au><au>LI YONG</au><au>XU HONGHUA</au><au>YIN LAIBIN</au><au>WANG LINGYAN</au><au>CHEN SHOULONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Transformer voiceprint spectrum feature enhancement method and system based on weight allocation</title><date>2023-10-13</date><risdate>2023</risdate><abstract>The invention discloses a transformer spectrum feature enhancement method and system based on weight allocation. Firstly, acquisition, noise reduction and spectrum analysis of acoustic signals of the transformer are carried out; secondly, defining different frequency bands as an interference section and an effective section according to amplitudes of different frequency components in an actual frequency spectrum, and performing reference weight calculation for different frequency band types; and finally performing enhancement processing on the spectrum features based on a reference weight calculation result, and verifying the effectiveness of the method based on the accuracy of state prediction before and after enhancement. According to the method, information such as frequency component amplitude and frequency bandwidth in the original frequency spectrum of the signal is analyzed and processed to form a method capable of analyzing reference weights of different frequencies according to the actual frequency s</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116884417A |
| 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 | Transformer voiceprint spectrum feature enhancement method and system based on weight allocation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T01%3A44%3A26IST&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=HE%20PING&rft.date=2023-10-13&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116884417A%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 |