Noise estimation method and related device
The invention provides a noise estimation method and a related device, and the method comprises the steps: judging whether each frame in an audio signal comprises a voice signal or not through voice activity detection, and obtaining a judgment result; the voice existence probability of each frequenc...
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 | PAN KAIDA QIN YAGUANG |
| description | The invention provides a noise estimation method and a related device, and the method comprises the steps: judging whether each frame in an audio signal comprises a voice signal or not through voice activity detection, and obtaining a judgment result; the voice existence probability of each frequency point of each frame in the audio signal is determined through minimum value tracking, and the voice existence probability is updated according to a judgment result so that the voice existence probability of each frequency point of each frame which does not contain the voice signal can be set to be zero; the noise of the audio signal is estimated by recursive averaging based on the updated speech presence probability. According to the invention, the noise estimation effect in a low signal-to-noise ratio and non-stationary noise environment can be effectively improved.
本公开提供了一种噪声估计方法和相关装置，该噪声估计方法包括：通过语音活性检测判断音频信号中各帧是否包含语音信号，得到判断结果；通过最小值跟踪确定音频信号中各帧的每个频点的语音存在概率，并根据判断结果更新语音存在概率以使不包含语音信号的各帧的每个频点的语音存在概率置零；基于更新后的语音存在概率，通 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115631762A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115631762A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115631762A3</originalsourceid><addsrcrecordid>eNrjZNDyy88sTlVILS7JzE0syczPU8hNLcnIT1FIzEtRKErNSSxJTVFISS3LTE7lYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhqZmxobmZkaOxsSoAQAqPSjx</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Noise estimation method and related device</title><source>esp@cenet</source><creator>PAN KAIDA ; QIN YAGUANG</creator><creatorcontrib>PAN KAIDA ; QIN YAGUANG</creatorcontrib><description>The invention provides a noise estimation method and a related device, and the method comprises the steps: judging whether each frame in an audio signal comprises a voice signal or not through voice activity detection, and obtaining a judgment result; the voice existence probability of each frequency point of each frame in the audio signal is determined through minimum value tracking, and the voice existence probability is updated according to a judgment result so that the voice existence probability of each frequency point of each frame which does not contain the voice signal can be set to be zero; the noise of the audio signal is estimated by recursive averaging based on the updated speech presence probability. According to the invention, the noise estimation effect in a low signal-to-noise ratio and non-stationary noise environment can be effectively improved.
本公开提供了一种噪声估计方法和相关装置，该噪声估计方法包括：通过语音活性检测判断音频信号中各帧是否包含语音信号，得到判断结果；通过最小值跟踪确定音频信号中各帧的每个频点的语音存在概率，并根据判断结果更新语音存在概率以使不包含语音信号的各帧的每个频点的语音存在概率置零；基于更新后的语音存在概率，通</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=20230120&DB=EPODOC&CC=CN&NR=115631762A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230120&DB=EPODOC&CC=CN&NR=115631762A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>PAN KAIDA</creatorcontrib><creatorcontrib>QIN YAGUANG</creatorcontrib><title>Noise estimation method and related device</title><description>The invention provides a noise estimation method and a related device, and the method comprises the steps: judging whether each frame in an audio signal comprises a voice signal or not through voice activity detection, and obtaining a judgment result; the voice existence probability of each frequency point of each frame in the audio signal is determined through minimum value tracking, and the voice existence probability is updated according to a judgment result so that the voice existence probability of each frequency point of each frame which does not contain the voice signal can be set to be zero; the noise of the audio signal is estimated by recursive averaging based on the updated speech presence probability. According to the invention, the noise estimation effect in a low signal-to-noise ratio and non-stationary noise environment can be effectively improved.
本公开提供了一种噪声估计方法和相关装置，该噪声估计方法包括：通过语音活性检测判断音频信号中各帧是否包含语音信号，得到判断结果；通过最小值跟踪确定音频信号中各帧的每个频点的语音存在概率，并根据判断结果更新语音存在概率以使不包含语音信号的各帧的每个频点的语音存在概率置零；基于更新后的语音存在概率，通</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>eNrjZNDyy88sTlVILS7JzE0syczPU8hNLcnIT1FIzEtRKErNSSxJTVFISS3LTE7lYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhqZmxobmZkaOxsSoAQAqPSjx</recordid><startdate>20230120</startdate><enddate>20230120</enddate><creator>PAN KAIDA</creator><creator>QIN YAGUANG</creator><scope>EVB</scope></search><sort><creationdate>20230120</creationdate><title>Noise estimation method and related device</title><author>PAN KAIDA ; QIN YAGUANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115631762A3</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>PAN KAIDA</creatorcontrib><creatorcontrib>QIN YAGUANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>PAN KAIDA</au><au>QIN YAGUANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Noise estimation method and related device</title><date>2023-01-20</date><risdate>2023</risdate><abstract>The invention provides a noise estimation method and a related device, and the method comprises the steps: judging whether each frame in an audio signal comprises a voice signal or not through voice activity detection, and obtaining a judgment result; the voice existence probability of each frequency point of each frame in the audio signal is determined through minimum value tracking, and the voice existence probability is updated according to a judgment result so that the voice existence probability of each frequency point of each frame which does not contain the voice signal can be set to be zero; the noise of the audio signal is estimated by recursive averaging based on the updated speech presence probability. According to the invention, the noise estimation effect in a low signal-to-noise ratio and non-stationary noise environment can be effectively improved.
本公开提供了一种噪声估计方法和相关装置，该噪声估计方法包括：通过语音活性检测判断音频信号中各帧是否包含语音信号，得到判断结果；通过最小值跟踪确定音频信号中各帧的每个频点的语音存在概率，并根据判断结果更新语音存在概率以使不包含语音信号的各帧的每个频点的语音存在概率置零；基于更新后的语音存在概率，通</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115631762A |
| 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 | Noise estimation method and related device |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T18%3A49%3A44IST&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=PAN%20KAIDA&rft.date=2023-01-20&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115631762A%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 |