Audio AI JAGORA

Ma'aunin ingancin Magana na PESQ da STOI

PESQ da STOI daidaitattun ma'auni ne na haƙiƙa waɗanda ke ƙididdige yadda ingantaccen sautin magana da yadda ake iya fahimta, ba tare da buƙatar masu sauraron ɗan adam ba.

2 min karatuAn sabunta ta ƙarshe

Dubawa

They let engineers benchmark codecs, noise reducers, and speech-enhancement models automatically.

Zurfafa nutsewa

PESQ (Kimanin Ƙimar Magana), daidaitacce kamar ITU-T P.862, yana annabta ingancin magana, galibi don gwajin tarho da codec. Yana kwatanta siginar tunani mai tsabta zuwa wanda aka lalata kuma yana fitar da maki akan ma'aunin MOS-kamar (kimanin -0.5 zuwa 4.5), yin ƙirar tsinkayen sauraron ɗan adam. STOI (Maƙasudin Hankali na ɗan gajeren lokaci), wanda aka gabatar a cikin 2010, maimakon haka yana annabta fahimta: kalmomi nawa ne mai sauraro zai fahimta a zahiri. Yana daidaita envelopes na ɗan gajeren lokaci na magana mai tsafta da sarrafawa a cikin madaukai na mitar, yana samar da maki daga 0 zuwa 1. Dukansu ma'auni ne na kutsawa (tushen tunani). PESQ ya amsa 'yana da kyau?' yayin da STOI ya amsa 'za ku iya gane shi?' Tare su ne tsoffin kayan aikin tantancewa don haɓaka magana, ƙiyayya, da tsarin ɓarna.

Fahimtar Fasaha

Duk ma'auni biyun suna tsoma baki: suna daidaita ma'ana mai tsabta tare da siginar da aka lalata kafin zura kwallo. Taswirorin PESQ duka suna sigina akan ma'aunin ƙarar murya na psychoacoustic (Bark bands), yana ƙididdige rikicewar fahimta akan lokaci, kuma yana mayar da shi zuwa ƙimar MOS. STOI yana raba magana zuwa rukunoni na octave ɗaya bisa uku, yana ɗaukar gajerun ~400 ms sassan ambulaf, shirye-shiryen bidiyo kuma ya daidaita su, sannan yana ƙididdige alaƙa tsakanin tunani da ƙasƙantar ambulaf. Matsakaicin waɗannan alaƙa yana haifar da makin 0-to-1.

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 Ma'aunin ingancin Maganar PESQ da STOI

Saboda PESQ da STOI suna buƙatar tunani mai tsafta, bincike yana juyawa zuwa ga waɗanda ba su da ƙarfi, ma'auni marasa ma'ana kamar DNSMOS da NISQA waɗanda ke da ƙima daga siginar ƙasƙanci kaɗai ta amfani da hanyoyin sadarwa na jijiyoyi. Hakanan an horar da sabbin ƙirar zurfafan koyo don tsinkayar MOS na ɗan adam kai tsaye. Har yanzu, PESQ da STOI sun kasance maƙasudin ma'auni, kuma wani mahimmin yanayin yana sanya su bambanta ta yadda za'a iya amfani da su kai tsaye azaman ayyukan asarar horo don cibiyoyin haɓaka magana maimakon kawai a matsayin kimantawa bayan-gaskiya.

Aiwatar da Gaskiyar Duniya

Benchmarking haɓaka magana da ƙira-ƙulla amo akan daidaitattun saitin gwaji

Kwatanta tarho da ingancin codec na VoIP yayin aikin injiniyan hanyar sadarwa

Tunatar da taimakon ji da sarrafa cochlear-implant don iyakar fahimta

Tabbatar da algorithms na ɓarna a cikin taro da bututun taimakon murya

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

1

Sami tabbataccen izini don ɗaukar murya, cloning, da sake amfani.

2

Gwajin ingantattun masu magana daban-daban da yanayin baya.

3

Ƙayyade lokacin da dole ne ɗan adam ya duba ko ya amince da abubuwan da aka fitar.

4

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 PESQ and STOI Speech Quality Metrics quiz

Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.

Fara tambayoyi

Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation

Jagora na gaba

Ingantacciyar Maganar Magana

Tambayoyin da ake yawan yi

What is PESQ and STOI Speech Quality Metrics?

PESQ da STOI daidaitattun ma'auni ne na haƙiƙa waɗanda ke ƙididdige yadda ingantaccen sautin magana da yadda ake iya fahimta, ba tare da buƙatar masu sauraron ɗan adam ba. Suna barin injiniyoyi suyi alamar codecs, masu rage amo, da ƙirar haɓaka magana ta atomatik.

Menene PESQ da farko ke aunawa?

PESQ (ITU-T P.862) yayi tsinkaya tsinkayar ingancin magana akan sikelin MOS.

Menene STOI da farko ke hasashen?

STOI yana ƙididdige basira, watau yadda za a iya fahimtar magana, akan sikelin 0-to-1.

Dukansu PESQ da STOI an siffanta su a matsayin ma'auni na 'shigarwa'. Menene ma'anar hakan?

Ma'auni na kutsawa suna kwatanta ƙasƙantar siginar da maƙasudi mai tsabta don ƙididdige maki.

Menene madaidaicin kewayon maki na STOI?

STOI yana fitar da ƙima tsakanin 0 da 1, inda mafi girma yana nufin ƙarin fahimta.

PESQ yana ƙirar jin ɗan adam ta amfani da wane nau'in sikelin mitar fahimta?

Taswirorin PESQ suna sigina kan wakilcin ƙarar hankali ta amfani da sarrafa Bark-band.