Model training method and device, speaking topic evaluation method and device and computer storage medium
The invention provides a model training method and device, a speaking topic evaluation method and device and a computer storage medium. The model training method comprises the following steps: acquiring to-be-evaluated voice and corresponding evaluation content; extracting an audio sequence and a te...
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 | WU KUI WANG BINGJUE HU GUOPING SHENG ZHICHAO LIU CONG LI HAO WANG SHIJIN ZHANG KAIBO |
| description | The invention provides a model training method and device, a speaking topic evaluation method and device and a computer storage medium. The model training method comprises the following steps: acquiring to-be-evaluated voice and corresponding evaluation content; extracting an audio sequence and a text sequence of the to-be-evaluated voice; obtaining a prediction evaluation score of the to-be-evaluated voice based on the voice prediction features of the audio sequence and the semantic prediction features of the text sequence and the evaluation content; and training the topic evaluation model according to the real evaluation score and the predicted evaluation score of the to-be-evaluated voice. Through the above mode, the voice prediction features and the semantic prediction features are used, and the scoring accuracy is improved.
本申请提出一种模型训练、说话题评测方法、装置及计算机存储介质。所述模型训练方法包括：获取待评测语音，以及对应的评测内容；提取所述待评测语音的音频序列和文本序列；基于所述音频序列的语音预测特征和所述文本序列以及所述评测内容的语义预测特征，获取所述待评测语音的预测评测分数；按照所述待评测语音的真实评测分数和预测评测分数，对所述说话题评测模型进行训练。通过上述方式，使用 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118335111A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118335111A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118335111A3</originalsourceid><addsrcrecordid>eNqNyrsKwkAQheE0FqK-w9hrsQTBVoJio5V9GHaPcUiys2QneX4v2NlYnR_ONy_kogEd2cASJTbUwx4aiGOggEk8NpQTuH1_pkk8YeJuZBONv_iTXvs0GgbKpgM3eLEgY78sZnfuMlbfXRTr0_FWnbdIWiMn9oiwuro6ty_LnXPuUP5jniq4QII</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model training method and device, speaking topic evaluation method and device and computer storage medium</title><source>esp@cenet</source><creator>WU KUI ; WANG BINGJUE ; HU GUOPING ; SHENG ZHICHAO ; LIU CONG ; LI HAO ; WANG SHIJIN ; ZHANG KAIBO</creator><creatorcontrib>WU KUI ; WANG BINGJUE ; HU GUOPING ; SHENG ZHICHAO ; LIU CONG ; LI HAO ; WANG SHIJIN ; ZHANG KAIBO</creatorcontrib><description>The invention provides a model training method and device, a speaking topic evaluation method and device and a computer storage medium. The model training method comprises the following steps: acquiring to-be-evaluated voice and corresponding evaluation content; extracting an audio sequence and a text sequence of the to-be-evaluated voice; obtaining a prediction evaluation score of the to-be-evaluated voice based on the voice prediction features of the audio sequence and the semantic prediction features of the text sequence and the evaluation content; and training the topic evaluation model according to the real evaluation score and the predicted evaluation score of the to-be-evaluated voice. Through the above mode, the voice prediction features and the semantic prediction features are used, and the scoring accuracy is improved.
本申请提出一种模型训练、说话题评测方法、装置及计算机存储介质。所述模型训练方法包括：获取待评测语音，以及对应的评测内容；提取所述待评测语音的音频序列和文本序列；基于所述音频序列的语音预测特征和所述文本序列以及所述评测内容的语义预测特征，获取所述待评测语音的预测评测分数；按照所述待评测语音的真实评测分数和预测评测分数，对所述说话题评测模型进行训练。通过上述方式，使用</description><language>chi ; eng</language><subject>ACOUSTICS ; CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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&date=20240712&DB=EPODOC&CC=CN&NR=118335111A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240712&DB=EPODOC&CC=CN&NR=118335111A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU KUI</creatorcontrib><creatorcontrib>WANG BINGJUE</creatorcontrib><creatorcontrib>HU GUOPING</creatorcontrib><creatorcontrib>SHENG ZHICHAO</creatorcontrib><creatorcontrib>LIU CONG</creatorcontrib><creatorcontrib>LI HAO</creatorcontrib><creatorcontrib>WANG SHIJIN</creatorcontrib><creatorcontrib>ZHANG KAIBO</creatorcontrib><title>Model training method and device, speaking topic evaluation method and device and computer storage medium</title><description>The invention provides a model training method and device, a speaking topic evaluation method and device and a computer storage medium. The model training method comprises the following steps: acquiring to-be-evaluated voice and corresponding evaluation content; extracting an audio sequence and a text sequence of the to-be-evaluated voice; obtaining a prediction evaluation score of the to-be-evaluated voice based on the voice prediction features of the audio sequence and the semantic prediction features of the text sequence and the evaluation content; and training the topic evaluation model according to the real evaluation score and the predicted evaluation score of the to-be-evaluated voice. Through the above mode, the voice prediction features and the semantic prediction features are used, and the scoring accuracy is improved.
本申请提出一种模型训练、说话题评测方法、装置及计算机存储介质。所述模型训练方法包括：获取待评测语音，以及对应的评测内容；提取所述待评测语音的音频序列和文本序列；基于所述音频序列的语音预测特征和所述文本序列以及所述评测内容的语义预测特征，获取所述待评测语音的预测评测分数；按照所述待评测语音的真实评测分数和预测评测分数，对所述说话题评测模型进行训练。通过上述方式，使用</description><subject>ACOUSTICS</subject><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</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>eNqNyrsKwkAQheE0FqK-w9hrsQTBVoJio5V9GHaPcUiys2QneX4v2NlYnR_ONy_kogEd2cASJTbUwx4aiGOggEk8NpQTuH1_pkk8YeJuZBONv_iTXvs0GgbKpgM3eLEgY78sZnfuMlbfXRTr0_FWnbdIWiMn9oiwuro6ty_LnXPuUP5jniq4QII</recordid><startdate>20240712</startdate><enddate>20240712</enddate><creator>WU KUI</creator><creator>WANG BINGJUE</creator><creator>HU GUOPING</creator><creator>SHENG ZHICHAO</creator><creator>LIU CONG</creator><creator>LI HAO</creator><creator>WANG SHIJIN</creator><creator>ZHANG KAIBO</creator><scope>EVB</scope></search><sort><creationdate>20240712</creationdate><title>Model training method and device, speaking topic evaluation method and device and computer storage medium</title><author>WU KUI ; WANG BINGJUE ; HU GUOPING ; SHENG ZHICHAO ; LIU CONG ; LI HAO ; WANG SHIJIN ; ZHANG KAIBO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118335111A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>ACOUSTICS</topic><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</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>WU KUI</creatorcontrib><creatorcontrib>WANG BINGJUE</creatorcontrib><creatorcontrib>HU GUOPING</creatorcontrib><creatorcontrib>SHENG ZHICHAO</creatorcontrib><creatorcontrib>LIU CONG</creatorcontrib><creatorcontrib>LI HAO</creatorcontrib><creatorcontrib>WANG SHIJIN</creatorcontrib><creatorcontrib>ZHANG KAIBO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU KUI</au><au>WANG BINGJUE</au><au>HU GUOPING</au><au>SHENG ZHICHAO</au><au>LIU CONG</au><au>LI HAO</au><au>WANG SHIJIN</au><au>ZHANG KAIBO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model training method and device, speaking topic evaluation method and device and computer storage medium</title><date>2024-07-12</date><risdate>2024</risdate><abstract>The invention provides a model training method and device, a speaking topic evaluation method and device and a computer storage medium. The model training method comprises the following steps: acquiring to-be-evaluated voice and corresponding evaluation content; extracting an audio sequence and a text sequence of the to-be-evaluated voice; obtaining a prediction evaluation score of the to-be-evaluated voice based on the voice prediction features of the audio sequence and the semantic prediction features of the text sequence and the evaluation content; and training the topic evaluation model according to the real evaluation score and the predicted evaluation score of the to-be-evaluated voice. Through the above mode, the voice prediction features and the semantic prediction features are used, and the scoring accuracy is improved.
本申请提出一种模型训练、说话题评测方法、装置及计算机存储介质。所述模型训练方法包括：获取待评测语音，以及对应的评测内容；提取所述待评测语音的音频序列和文本序列；基于所述音频序列的语音预测特征和所述文本序列以及所述评测内容的语义预测特征，获取所述待评测语音的预测评测分数；按照所述待评测语音的真实评测分数和预测评测分数，对所述说话题评测模型进行训练。通过上述方式，使用</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118335111A |
| source | esp@cenet |
| subjects | ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION |
| title | Model training method and device, speaking topic evaluation method and device and computer storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T23%3A26%3A15IST&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=WU%20KUI&rft.date=2024-07-12&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118335111A%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 |