Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method
The invention provides a Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method which comprises the following steps: firstly, extracting features of a to-be-converted voice, and sending a Mel Frequency cepstrum coefficient of the to-be-conv...
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 | SUN MENG CAO TIEYONG ZENG XIN LI LI MIAO XIAOKONG ZHANG XIONGWEI ZHENG CHANGYAN |
| description | The invention provides a Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method which comprises the following steps: firstly, extracting features of a to-be-converted voice, and sending a Mel Frequency cepstrum coefficient of the to-be-converted voice into a feature conversion network for conversion to obtain a converted Mel Frequency cepstrum coefficient; then up-sampling an aperiodic frequency of the to-be-converted voice, a linearly converted fundamental tone frequency and the converted Mel Frequency cepstrum coefficient, and sending into a voice generation network to obtain a pre-generated voice, and sending a Mel Frequency cepstrum coefficient of the pre-generated voice into a post-processing network for post-processing; andup-sampling the post-treated Mel Frequency cepstrum coefficient, the aperiodic frequency of the to-be-converted voice and the linearly converted fundamental tone frequency, and sending into the voicegeneration network to gene |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN109767778A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN109767778A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN109767778A3</originalsourceid><addsrcrecordid>eNqNjLEKwjAUALs4iPoPz02HgCIYHW1RHNoOWnAsIXm1wTavvKQV_94OfoDTwXHcNOLYivReZLCKrbGMOlhyqhEpuSfca-IgCuQWMmyJP3BD3TOjC5Bjz6oZEd7EL78G5Qw81ICjgar3aGAgqxE0uQHZj1toMdRk5tGkUo3HxY-zaHk5F8lVYEcl-k5pdBjKJN9ujnIvpTycdv80Xwp2Qw0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method</title><source>esp@cenet</source><creator>SUN MENG ; CAO TIEYONG ; ZENG XIN ; LI LI ; MIAO XIAOKONG ; ZHANG XIONGWEI ; ZHENG CHANGYAN</creator><creatorcontrib>SUN MENG ; CAO TIEYONG ; ZENG XIN ; LI LI ; MIAO XIAOKONG ; ZHANG XIONGWEI ; ZHENG CHANGYAN</creatorcontrib><description>The invention provides a Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method which comprises the following steps: firstly, extracting features of a to-be-converted voice, and sending a Mel Frequency cepstrum coefficient of the to-be-converted voice into a feature conversion network for conversion to obtain a converted Mel Frequency cepstrum coefficient; then up-sampling an aperiodic frequency of the to-be-converted voice, a linearly converted fundamental tone frequency and the converted Mel Frequency cepstrum coefficient, and sending into a voice generation network to obtain a pre-generated voice, and sending a Mel Frequency cepstrum coefficient of the pre-generated voice into a post-processing network for post-processing; andup-sampling the post-treated Mel Frequency cepstrum coefficient, the aperiodic frequency of the to-be-converted voice and the linearly converted fundamental tone frequency, and sending into the voicegeneration network to gene</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>2019</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=20190517&DB=EPODOC&CC=CN&NR=109767778A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190517&DB=EPODOC&CC=CN&NR=109767778A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SUN MENG</creatorcontrib><creatorcontrib>CAO TIEYONG</creatorcontrib><creatorcontrib>ZENG XIN</creatorcontrib><creatorcontrib>LI LI</creatorcontrib><creatorcontrib>MIAO XIAOKONG</creatorcontrib><creatorcontrib>ZHANG XIONGWEI</creatorcontrib><creatorcontrib>ZHENG CHANGYAN</creatorcontrib><title>Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method</title><description>The invention provides a Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method which comprises the following steps: firstly, extracting features of a to-be-converted voice, and sending a Mel Frequency cepstrum coefficient of the to-be-converted voice into a feature conversion network for conversion to obtain a converted Mel Frequency cepstrum coefficient; then up-sampling an aperiodic frequency of the to-be-converted voice, a linearly converted fundamental tone frequency and the converted Mel Frequency cepstrum coefficient, and sending into a voice generation network to obtain a pre-generated voice, and sending a Mel Frequency cepstrum coefficient of the pre-generated voice into a post-processing network for post-processing; andup-sampling the post-treated Mel Frequency cepstrum coefficient, the aperiodic frequency of the to-be-converted voice and the linearly converted fundamental tone frequency, and sending into the voicegeneration network to gene</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjLEKwjAUALs4iPoPz02HgCIYHW1RHNoOWnAsIXm1wTavvKQV_94OfoDTwXHcNOLYivReZLCKrbGMOlhyqhEpuSfca-IgCuQWMmyJP3BD3TOjC5Bjz6oZEd7EL78G5Qw81ICjgar3aGAgqxE0uQHZj1toMdRk5tGkUo3HxY-zaHk5F8lVYEcl-k5pdBjKJN9ujnIvpTycdv80Xwp2Qw0</recordid><startdate>20190517</startdate><enddate>20190517</enddate><creator>SUN MENG</creator><creator>CAO TIEYONG</creator><creator>ZENG XIN</creator><creator>LI LI</creator><creator>MIAO XIAOKONG</creator><creator>ZHANG XIONGWEI</creator><creator>ZHENG CHANGYAN</creator><scope>EVB</scope></search><sort><creationdate>20190517</creationdate><title>Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method</title><author>SUN MENG ; CAO TIEYONG ; ZENG XIN ; LI LI ; MIAO XIAOKONG ; ZHANG XIONGWEI ; ZHENG CHANGYAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN109767778A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</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>SUN MENG</creatorcontrib><creatorcontrib>CAO TIEYONG</creatorcontrib><creatorcontrib>ZENG XIN</creatorcontrib><creatorcontrib>LI LI</creatorcontrib><creatorcontrib>MIAO XIAOKONG</creatorcontrib><creatorcontrib>ZHANG XIONGWEI</creatorcontrib><creatorcontrib>ZHENG CHANGYAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SUN MENG</au><au>CAO TIEYONG</au><au>ZENG XIN</au><au>LI LI</au><au>MIAO XIAOKONG</au><au>ZHANG XIONGWEI</au><au>ZHENG CHANGYAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method</title><date>2019-05-17</date><risdate>2019</risdate><abstract>The invention provides a Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method which comprises the following steps: firstly, extracting features of a to-be-converted voice, and sending a Mel Frequency cepstrum coefficient of the to-be-converted voice into a feature conversion network for conversion to obtain a converted Mel Frequency cepstrum coefficient; then up-sampling an aperiodic frequency of the to-be-converted voice, a linearly converted fundamental tone frequency and the converted Mel Frequency cepstrum coefficient, and sending into a voice generation network to obtain a pre-generated voice, and sending a Mel Frequency cepstrum coefficient of the pre-generated voice into a post-processing network for post-processing; andup-sampling the post-treated Mel Frequency cepstrum coefficient, the aperiodic frequency of the to-be-converted voice and the linearly converted fundamental tone frequency, and sending into the voicegeneration network to gene</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN109767778A |
| 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 | Bi-LSTM (Bidirectional-Long Short-Term Memory Recurrent Neural Networks) and WaveNet fused voice conversion method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T21%3A49%3A47IST&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=SUN%20MENG&rft.date=2019-05-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN109767778A%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 |