Rabuwar Magana da Matsalar Jam'iyyar Cocktail
Rarrabuwar magana shine aikin ja da muryoyin ɗaiɗaikun ban da rikodin da mutane da yawa ke magana lokaci ɗaya.
Dubawa
It tackles the 'cocktail party problem' that humans solve effortlessly but machines find genuinely hard.
Zurfafa nutsewa
A wata ƙungiya mai hayaniya, za ku iya mai da hankali kan tattaunawa ɗaya yayin da kuke tace sauran, ikon da masanin ilimin halayyar ɗan adam Colin Cherry ya ba da sunan 'matsalar jam'iyyar cocktail' a 1953. Kwamfuta suna kokawa saboda muryoyin da suka mamaye juna suna haɗuwa a cikin nau'in igiyar ruwa guda ɗaya, kuma tsarin bai san da yawa masu magana da yawa ba ko kuma wane sauti na wane ne. Algorithms na raba magana suna ɗaukar wannan gauraye audio kuma suna fitar da keɓantaccen waƙa mai tsafta ga kowane mai magana. Hanyoyi na farko sun yi amfani da hanyoyin ƙididdiga da tsararrun makirufo don yin amfani da alamun sarari. Ci gaban ya zo tare da ƙirar ilmantarwa mai zurfi kamar Deep Clustering da TasNet/Conv-TasNet, waɗanda ke koyon rufe fuska ko sake gina kowace murya kai tsaye daga tsarin igiyar ruwa, koda da makirufo ɗaya.
Fahimtar Fasaha
Tsarukan da yawa suna aiki a cikin yanki na koyo ko spectrogram: cibiyar sadarwar jijiyoyi tana kimanta 'mask' ga kowane mai magana wanda, lokacin da aka yi amfani da shi ga cakuda, ke ware wannan muryar. Samfuran yanki na lokaci kamar Conv-TasNet sun tsallake sitirogram gaba ɗaya kuma suna aiki akan ɗanyen samfuran don ingantaccen aminci da ƙarancin jinkiri. Babban ƙalubalen shine matsalar haɓakawa, yanke shawarar waɗanne taswirorin tashar fitarwa zuwa wanne mai magana, wanda aka warware tare da horarwar da ba ta dace ba don haka ba a hukunta ƙirar don odar fitarwa.
Dabarun Tasiri
Shiga ku isa
Yana inganta samun dama ta hanyar rubutu, ba da labari, da mu'amalar murya.
Kudin da kasafin kuɗi
Ƙungiyoyin kafofin watsa labaru na iya jigilar sauti mai gogewa cikin sauri tare da ƙaramin kasafin kuɗi.
Gudu da sikelin
Tsarin fuskantar abokin ciniki na iya aiwatar da hulɗar magana a mafi girman ma'auni.
Makomar Rabewar Magana da Matsalolin Jam'iyyar Cocktail
Rabuwa yana tafiya zuwa buɗe, yanayin duniya na ainihi: wanda ba a sani ba da canza lambobi na lasifika, ɗakuna masu maimaitawa, da ci gaba da yawo mai jiwuwa. Cire mai magana da manufa, inda kuke ba samfurin gajeriyar samfurin murya don fitar da mutumin kawai, yana tashi da sauri. Haɗe-haɗen samfuran gani da sauti suna amfani da motsin leɓe don ɓata muryoyin. Yi tsammanin waɗannan iyawar da ke kunshe cikin na'urorin ji, belun kunne, da rubutun taro, barin na'urori su haskaka duk wanda kuke son ji.
Aiwatar da Gaskiyar Duniya
Kayan aikin rubutun taron sun raba masu lasifikan da ke kan juna don haka ana dangana kalmomin kowane mutum daidai a cikin bayanin kula.
Na'urorin ji na ci gaba suna ware mai magana ɗaya a cikin cunkoson abinci don sauƙaƙa tattaunawa ga mai sawa.
Kiɗa da samar da kwasfan fayiloli suna amfani da rarrabuwa don raba muryoyin daga kayan kida ko karkatar da magana tsakanin runduna.
Bututun tantance magana sun riga sun keɓance gauraye mai jiwuwa don kowace murya za a iya rubuta su daidai.
Hatsari & Tsare-tsare
Rashin amfani da murya da haɗarin kwaikwaya yana ƙaruwa lokacin da aka rasa izini.
Daidaituwa na iya faɗuwa cikin lafuzza, yaruka, ko mahalli masu hayaniya.
Ana iya kuskuren sauti na roba don ingantacciyar magana ba tare da bayyananniyar lakabi ba.
Taswirar Hanya
Sami tabbataccen izini don ɗaukar murya, cloning, da sake amfani.
Gwajin ingantattun masu magana daban-daban da yanayin baya.
Ƙayyade lokacin da dole ne ɗan adam ya duba ko ya amince da abubuwan da aka fitar.
Yi lakabin sauti na roba da kuma adana bayanan da aka tabbatar don yin lissafi.
Ci gaba da Bincike
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 Speech Separation and the Cocktail Party Problem 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
Jagora na gaba
Demucs Music Source Rabe
Tambayoyin da ake yawan yi
What is Speech Separation and the Cocktail Party Problem?
Rarrabuwar magana shine aikin ja da muryoyin ɗaiɗaikun ban da rikodin da mutane da yawa ke magana lokaci ɗaya. Yana magance matsalar 'cocktail party' wanda mutane ke warwarewa ba tare da wahala ba amma injuna suna samun wahala da gaske.
Menene matsalar jam'iyyar 'cocktail party'?
Colin Cherry ne ya ƙirƙira shi a shekara ta 1953, ya kwatanta ƙalubalen halartan mai magana ɗaya sa’ad da mutane da yawa ke magana lokaci ɗaya.
Menene fitowar tsarin raba magana da aka ba gaurayawan rikodi na masu magana da yawa?
Rabuwa yana samar da tsaftataccen rafi guda ɗaya ga kowane mai magana, yana kwance muryoyin da suka mamaye juna.
Menene Conv-TasNet ya bambanta da yawancin hanyoyin rabuwa na farko?
Conv-TasNet yana amfani da rikodin koyo akan ɗanyen sauti maimakon ƙayyadaddun spectrogram, yana ba da damar ingantaccen aminci, rarrabuwar kawuna.
Yaya yawancin cibiyoyin sadarwar rabuwa ke ware muryar mutum ɗaya daga cakuɗen?
Samfurin yana annabta abin rufe fuska da mai magana; shafa shi a cikin cakuda yana kiyaye abun cikin mai magana kuma yana danne sauran.
Menene 'harar mai magana'?
Maimakon raba kowa da kowa, kuna samar da alamar murya kuma samfurin yana fitar da mai magana kawai.