AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS
The invention relates to an automatic speech recognition system with integrated perceptual based adversarial audio attacks. The invention relates to a computer-implemented method for creating a combined audio signal in a speech recognition system, and the method includes the steps: sampling the audi...
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 | SZURLEY JOSEPH KOLTER JEREMY |
| description | The invention relates to an automatic speech recognition system with integrated perceptual based adversarial audio attacks. The invention relates to a computer-implemented method for creating a combined audio signal in a speech recognition system, and the method includes the steps: sampling the audio input signal to generate a time-domain sampled input signal, then converting the time-domain sampled input signal to a frequency-domain input signal, afterwards generating perceptual weights in response to frequency components of critical bands of the frequency-domain input signal, creating a time-domain adversary signal in response to the perceptual weights; and combining the time-domain adversary signal with the audio input signal to create a combined audio signal, wherein a speech processing of the combined audio signal will output a different result from speech processing of the audio input signal.
本发明涉及解决基于感知的对抗音频攻击的自动语音识别系统。一种用于在语音识别系统中产生组合音频信号的计算机实施的方法，方法包括以下步骤：对音频输入信号进行采样，以生成时域采样的输入信号，然后将时域采样的输入信号转换为频域输入信 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112086093A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112086093A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112086093A3</originalsourceid><addsrcrecordid>eNqNyjEKwkAQQNE0FqLeYTyAkBgQLcfJmAya3bA7q9gYgqyVaCDeH1N4AKsPjz9NbhjU1qhC4BtmqsAx2dKIijXgr165hotoBWKUS4fKBTTsiBsNeII9-hGwOLPz6GQUDIVYQFWko58nk0f3HOLi11myPLBStYr9u41D393jK35aMlm2TrebdJdj_s_zBUv5Myg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS</title><source>esp@cenet</source><creator>SZURLEY JOSEPH ; KOLTER JEREMY</creator><creatorcontrib>SZURLEY JOSEPH ; KOLTER JEREMY</creatorcontrib><description>The invention relates to an automatic speech recognition system with integrated perceptual based adversarial audio attacks. The invention relates to a computer-implemented method for creating a combined audio signal in a speech recognition system, and the method includes the steps: sampling the audio input signal to generate a time-domain sampled input signal, then converting the time-domain sampled input signal to a frequency-domain input signal, afterwards generating perceptual weights in response to frequency components of critical bands of the frequency-domain input signal, creating a time-domain adversary signal in response to the perceptual weights; and combining the time-domain adversary signal with the audio input signal to create a combined audio signal, wherein a speech processing of the combined audio signal will output a different result from speech processing of the audio input signal.
本发明涉及解决基于感知的对抗音频攻击的自动语音识别系统。一种用于在语音识别系统中产生组合音频信号的计算机实施的方法，方法包括以下步骤：对音频输入信号进行采样，以生成时域采样的输入信号，然后将时域采样的输入信号转换为频域输入信</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>2020</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=20201215&DB=EPODOC&CC=CN&NR=112086093A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76302</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201215&DB=EPODOC&CC=CN&NR=112086093A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SZURLEY JOSEPH</creatorcontrib><creatorcontrib>KOLTER JEREMY</creatorcontrib><title>AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS</title><description>The invention relates to an automatic speech recognition system with integrated perceptual based adversarial audio attacks. The invention relates to a computer-implemented method for creating a combined audio signal in a speech recognition system, and the method includes the steps: sampling the audio input signal to generate a time-domain sampled input signal, then converting the time-domain sampled input signal to a frequency-domain input signal, afterwards generating perceptual weights in response to frequency components of critical bands of the frequency-domain input signal, creating a time-domain adversary signal in response to the perceptual weights; and combining the time-domain adversary signal with the audio input signal to create a combined audio signal, wherein a speech processing of the combined audio signal will output a different result from speech processing of the audio input signal.
本发明涉及解决基于感知的对抗音频攻击的自动语音识别系统。一种用于在语音识别系统中产生组合音频信号的计算机实施的方法，方法包括以下步骤：对音频输入信号进行采样，以生成时域采样的输入信号，然后将时域采样的输入信号转换为频域输入信</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEKwkAQQNE0FqLeYTyAkBgQLcfJmAya3bA7q9gYgqyVaCDeH1N4AKsPjz9NbhjU1qhC4BtmqsAx2dKIijXgr165hotoBWKUS4fKBTTsiBsNeII9-hGwOLPz6GQUDIVYQFWko58nk0f3HOLi11myPLBStYr9u41D393jK35aMlm2TrebdJdj_s_zBUv5Myg</recordid><startdate>20201215</startdate><enddate>20201215</enddate><creator>SZURLEY JOSEPH</creator><creator>KOLTER JEREMY</creator><scope>EVB</scope></search><sort><creationdate>20201215</creationdate><title>AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS</title><author>SZURLEY JOSEPH ; KOLTER JEREMY</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112086093A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</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>SZURLEY JOSEPH</creatorcontrib><creatorcontrib>KOLTER JEREMY</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SZURLEY JOSEPH</au><au>KOLTER JEREMY</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS</title><date>2020-12-15</date><risdate>2020</risdate><abstract>The invention relates to an automatic speech recognition system with integrated perceptual based adversarial audio attacks. The invention relates to a computer-implemented method for creating a combined audio signal in a speech recognition system, and the method includes the steps: sampling the audio input signal to generate a time-domain sampled input signal, then converting the time-domain sampled input signal to a frequency-domain input signal, afterwards generating perceptual weights in response to frequency components of critical bands of the frequency-domain input signal, creating a time-domain adversary signal in response to the perceptual weights; and combining the time-domain adversary signal with the audio input signal to create a combined audio signal, wherein a speech processing of the combined audio signal will output a different result from speech processing of the audio input signal.
本发明涉及解决基于感知的对抗音频攻击的自动语音识别系统。一种用于在语音识别系统中产生组合音频信号的计算机实施的方法，方法包括以下步骤：对音频输入信号进行采样，以生成时域采样的输入信号，然后将时域采样的输入信号转换为频域输入信</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN112086093A |
| 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 | AUTOMATIC SPEECH RECOGNITION SYSTEM WITH INTEGRATED PERCEPTUAL BASED ADVERSARIAL AUDIO ATTACKS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T23%3A00%3A38IST&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=SZURLEY%20JOSEPH&rft.date=2020-12-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112086093A%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 |