Laburaren AI kyauta

Audio AI jagororiKyauta har abada.

117 jagororin turanci a sarari, tsayayyen hanyoyin koyo, da buɗe ɗakin karatu - wanda 501(c)(3) mai zaman kanta ta gina ta yadda kowa zai iya fahimtar AI na zamani.

117Jagoran kyauta
1Waƙoƙin jigo
~2 minKowane jagora
~4hLokacin karatu

Fara a nan

Biyar darussa na tushen sakamako

Kowane darasi ya haɗa da tabbataccen sakamako, ƙwarewar taswira, ayyukan yi, da babban dutse da aka yi amfani da shi.

Waƙoƙin jigo

Bincika ta hanya

Tsallaka zuwa yankin da kuke damuwa. Kowace waƙa tana da jagororin bayyanannun Ingilishi da yawa.

Cikakken ɗakin karatu

Duk jagora

117 na 1019 jagororin da aka nuna. Tace ta hanya ko bincike a sama.

Audio AI

Beamforming da Microphone Arrays

Beamforming yana amfani da makirufo da yawa don saurare ta hanyar da aka zaɓa, yana ƙara sauti daga manufa yayin da yake murkushe komai.

2 min karatuKaranta
Audio AI

Riffusion Spectrogram Diffusion

Riffusion hack ne mai wayo wanda ke haifar da kiɗa ta hanyar ɗaukar sauti azaman hoto: yana daidaita ƙirar Stable Diffusion hoton don fenti spectrograms, sannan…

2 min karatuKaranta
Audio AI

MusicLM: Hierarchical Semantic and Acoustic Tokens

Koyi yadda Google MusicLM ke amfani da ma'anar ma'anar ma'anar ma'ana da alamar sauti, SoundStream, da MuLan don juya saƙon rubutu zuwa kiɗan da ya dace.

2 min karatuKaranta
Audio AI

Haɓaka Maganar Noise2

Noise2Noise dabara ce ta horarwa wacce ke barin abin ƙira ya koyi cire surutu ba tare da taɓa ganin tsaftataccen tunani ba, ta hanyar koyo daga nau'i-nau'i na daban-m...

2 min karatuKaranta
Audio AI

Conv-TasNet Lokaci-Yankin Rabewa

Conv-TasNet cibiyar sadarwa ce ta jijiya wacce ke raba gauraye audio (kamar mutane biyu suna magana lokaci guda) ta yin aiki kai tsaye akan danyen sautin kalaman sauti maimakon…

2 min karatuKaranta
Audio AI

Rabuwar Hanyoyi Dual-Path RNN

Dual-Path RNN (DPRNN) gine-ginen rarrabuwar sauti ne wanda ke raba jerin fa'idodin sauti masu tsayi zuwa gajerun gungu-gungu da sarrafa su…

2 min karatuKaranta
Audio AI

Buɗe-Unmix Rabewar Kiɗa

Open-Unmix (UMX) shine tsarin ilmantarwa mai zurfi mai buɗewa wanda ke raba waƙa zuwa sassanta: murya, ganguna, bass, da sauran kayan kida.

2 min karatuKaranta
Audio AI

Daidaita Kalma Mai Tafiyar Lokaci

Daidaita kalmar raɗaɗi yana sanya kowace kalma da aka rubuta zuwa ainihin lokacin farawa da ƙarshen lokacin a cikin sautin.

2 min karatuKaranta
Audio AI

Tagging na kiɗa tare da masu canzawa

Alamar waƙar tana amfani da ƙirar mai canzawa don sauraron waƙa da tsinkaya alamomin siffa kamar nau'in, yanayi, kayan kida, da ɗan lokaci.

2 min karatuKaranta
Audio AI

Gano Farko a cikin Audio

Gano farawa yana gano daidai lokacin da bayanin kula, bugu, ko sautuna suka fara a cikin siginar sauti.

2 min karatuKaranta
Audio AI

MelGAN Generative Vocoder

MelGAN cikakken sauti ne na tushen GAN mai jujjuyawa wanda ke juya mel-spectrograms zuwa sifofin raƙuman sauti mai sauƙi a cikin wucewar gaba ɗaya cikin sauri.

2 min karatuKaranta
Audio AI

UnivNet Multi-Resolution Vocoder

UnivNet shine vocoder na GAN wanda ke yin hukunci don ƙirƙirar sauti ta amfani da ƙididdiga masu yawa da aka lissafta a ƙudurin STFT daban-daban, yana ƙara dalla-dalla dalla-dalla.

2 min karatuKaranta

Ya gama karantawa? Tabbatar da shi.

Check what you learned with a topic quiz, then explore our structured courses or work toward a certificate. Every guide stays free to read.