Nchọpụta mmemme ụda
Nchọpụta mmemme ụda (SED) na-achọpụta ihe ụda na-eme na iyi ọdịyo yana kpọmkwem mgbe ha malitere na kwụsị.
Nchịkọta
It turns raw audio into a labeled timeline, enabling machines to understand acoustic scenes.
Ime miri emi
Nchọpụta emume ụda na-agabiga naanị iji akara kpado obere vidiyo; ọ na-egosi oge mmalite na nkwụsị nke mmemme ọ bụla, dị ka nkịta na-agbọ site na 2.1 ruo 3.4 sekọnd mgbe ụgbọ ala na-agafe n'azụ. Nke a bụ ihe kpatara ya bụ nsogbu polyphonic n'ihi na ọtụtụ ụda nwere ike ime n'otu oge, yabụ ụdị ga-ejikwa ọtụtụ akara n'otu oge. A na-azụkarị sistemu na nhazi data dị ka AudioSet, DESED, ma ọ bụ UrbanSound8K. Ihe ịma aka DCASE kwa afọ akwalitela ọtụtụ ọganihu nke ubi ahụ. Ngwa sitere na nleba anya nchekwa ụlọ smart-ụlọ yana nleba anya anụ ọhịa ruo na ịchọpụta mmejọ igwe. Ihe ịma aka na-adịgide adịgide bụ akara na-adịghị ike, ebe obere vidiyo na-egosi na ihe omume mere mana ọ bụghị kpọmkwem mgbe.
Nghọta nka nka
Otu pipeline SED na-atụgharị ụda ka ọ bụrụ log-mel spectrogram, wee na-azụ ya na netwọkụ akwara ozi na-agbanwe agbanwe (CRNN) ma ọ bụ, na-arịwanye elu, ihe ntụgharị. N'ígwé nke CNN na-ejide ụkpụrụ oge oge mpaghara ebe ọ na-emegharị ugboro ugboro ma ọ bụ nlebara anya na-egosipụta ọnọdụ ọnọdụ nwa oge, na-ewepụta ohere ọ bụla maka klaasị mmemme ọ bụla. Iji mụta oge ziri ezi site na data akpọchiri adịghị ike, ụdị na-eji mmụta ọtụtụ ihe atụ na nlebara anya, na-egosipụta ọrụ ọkwa etiti site na akara ọkwa clip.
Mmetụta atụmatụ
Nweta na iru
Ọ na-eme ka nnweta ya dịkwuo mma site na ndegharị, ịkọ akụkọ, na ntụgharị olu.
Ọnụ ego na mmefu ego
Ndị otu mgbasa ozi nwere ike ibubata ọdịyo a na-egbu maramara ngwa ngwa site na iji obere mmefu ego.
Ọsọ na ọnụ ọgụgụ
Sistemụ na-eche ihu ndị ahịa nwere ike hazie mkparịta ụka n'ọtụtụ buru ibu.
Ọdịnihu nke nchọpụta ihe omume ụda
Ogige ahụ na-aga n'ihu n'ụdị ntọala ọdịyo a na-ahụ maka onwe ya nke a zụrụ azụ na nnukwu ụlọ ọrụ na-enweghị akara, emeziri nke ọma maka nchọpụta nwere data enweghị akara. Nchọpụta okwu mepere emepe na asụsụ, ebe ị rịọrọ maka ụda aka ike site na nkọwa ederede, na-apụta. Na-atụ anya ibunye ngwa ngwa siri ike maka obere oge, nleba anya na-echekwa nzuzo, yana njikọ siri ike na ihe mmetụta ndị ọzọ. Ịkwụsi ike na mkpọtụ, nkwughachi, gburugburu ụwa n'ezie ka bụ isi nyocha nyocha.
Mmejuputa n'ezie n'ụwa
Ngwa ụlọ smart na ihe enyemaka ịnụ ihe na-eme ka ndị ọrụ mara ka ha na-ese anwụrụ, iko na-agbaji, ma ọ bụ nwa na-ebe akwa.
Sistemụ nleba anya bioacoustic na-achọpụta oku nnụnụ, whale, ma ọ bụ ụmụ ahụhụ iji soro ụdị dị iche iche dị n'ime ọhịa.
Ngwá ọrụ nlekọta amụma na-ahụ ụda igwe na-adịghị mma n'ala ụlọ mmepụta ihe tupu akụrụngwa ada ada
Netwọk nlekota mkpọtụ nke obodo na-ekewa sirens, egbe egbe, okporo ụzọ na ihe owuwu maka nhazi obodo
Ihe ize ndụ & okporo ụzọ nche
Iji olu eme ihe na ihe egwu mpụta ga-abawanye mgbe nkwenye na-efu.
Izi ezi nwere ike ịdaba n'ofe ụda olu, olumba ma ọ bụ gburugburu mkpọtụ.
Enwere ike imehie ọdịyo sịntetik dị ka ezigbo okwu na-enweghị akara doro anya.
Map mmejuputa
Nweta nkwenye doro anya maka ijide olu, imechi, na ijigharị.
Nwale ogo n'ofe ndị na-ekwu okwu dị iche iche yana ọnọdụ ndabere.
Kọwaa mgbe mmadụ ga-enyocha ma ọ bụ kwado nsonye.
Deba aha ọdịyo sịntetik ma debe ndekọ ihe ndekọ maka ịza ajụjụ.
Nọgide na-eme nchọpụta
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Sound Event Detection quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Ntuziaka na-esote
Nchọpụta Deepfake Audio
Ajụjụ a na-ajụkarị
What is Sound Event Detection?
Nchọpụta mmemme ụda (SED) na-achọpụta ihe ụda na-eme na iyi ọdịyo yana kpọmkwem mgbe ha malitere na kwụsị. Ọ na-atụgharị ọdịyo raw ka ọ bụrụ usoro iheomume akpọrọ, na-enyere igwe aka ịghọta ihe nkiri egwu.
Kedu ihe dị iche na nchọpụta mmemme ụda na mkpado ọdịyo dị mfe?
SED na-akọwapụta ihe omume n'oge na mmalite na dechapụ timestamps, ebe ịkpado naanị akara ma ụda ọ dị ebe na obere vidiyo.
Kedu ihe kpatara eji akọwakarị nchọpụta ihe omume dị ka nsogbu polyphonic?
Ọdịda nke ụwa n'ezie na-enwekarị ọtụtụ mmemme na-ejikọta ọnụ n'otu oge, yabụ ihe nlereanya ahụ ga-ebu amụma ọtụtụ akara aha na-arụ ọrụ n'otu etiti.
Kedu ihe 'ịkpọ aha adịghị ike' pụtara na data ọzụzụ SED?
Mpempe akwụkwọ ndị na-adịghị ike na-egosi ọnụnọ nke mmemme na obere vidiyo na-enweghị ezigbo mmalite na oge nkwụsị, na-eme ka mmụta ziri ezi nwa oge sie ike karị.
Kedu ihe owuwu akwara na-ejikarị dị ka ọkpụkpụ azụ maka SED?
CRNN na-ejikọta akwa CNN nke na-ejide ụkpụrụ oge na-emegharị ugboro ugboro na-egosipụta ọnọdụ nwa oge, ụdị SED mara mma ugbu a nke ndị na-agbanwe agbanwe na-ejikọta ya.
Kedu ihe nnochite anya ntinye ka a na-enyekarị n'ụdị nchọpụta mmemme ụda?
A na-atụgharịkarị ọdịyo ka ọ bụrụ log-mel spectrogram, onyonyo na-ewe oge nke ụdị na-enyocha maka usoro ụda olu.