Umtapo wezincwadi we-AI wamahhala

Umsindo we-AI abaqondisiMahhala phakade.

117 imihlahlandlela yesiNgisi esicacile, izindlela zokufunda ezihlelekile, nomtapo wolwazi ovulekile — wakhiwe inhlangano engenzi nzuzo ye-501(c)(3) ezimele ukuze noma ubani aqonde i-AI yesimanje.

117Iziqondiso zamahhala
1Amathrekhi esihloko
~2 minNgomhlahlandlela
~4hIsikhathi sokufunda

Qala lapha

Ezinhlanu izifundo ezisekelwe emiphumeleni

Isifundo ngasinye sihlanganisa imiphumela esobala, amakhono afakwe kumephu, imisebenzi yokuzilolonga, kanye netshe eliyinhloko elisetshenzisiwe.

Amathrekhi esihloko

Phequlula ngethrekhi

Gxumela endaweni oyikhathalelayo. Wonke amathrekhi anemihlahlandlela eminingi yesiNgisi esilula.

Umtapo wolwazi ogcwele

Zonke iziqondiso

117 kwe 1019 imihlahlandlela ebonisiwe. Hlunga ngethrekhi noma sesha ngenhla.

Umsindo we-AI

Ukuhlonza Ingoma Yekhava

Ukuhlonzwa kwengoma yekhava kuthola lapho okurekhodiwe okubili okunomsindo ohluke kakhulu kuyingoma eyisisekelo efanayo - inguqulo ye-acoustic ebukhoma, i-remix...

2 min fundaFunda
Umsindo we-AI

I-DDSP Differentiable Audio Synthesis

I-DDSP (I-Differentiable Digital Signal Processing) ihlanganisa amabhulokhi wokwakha we-synthesizer wakudala ngamanethiwekhi e-neural, ukuze ukufunda okujulile kungalawula ama-oscillator...

2 min fundaFunda
Umsindo we-AI

I-VITS Ukuhlanganiswa Kwenkulumo Yokuphela-kuya-Ekupheleni

I-VITS imodeli yokuguqula umbhalo ube inkulumo eshintsha umbhalo ngokuqondile uwenze amaza omsindo angahluziwe kusistimu eyodwa eqeqeshiwe, yeqa ipayipi elivamile lezigaba ezimbili.

2 min fundaFunda
Umsindo we-AI

I-FastSpeech ne-Non-Autoregressive TTS

I-FastSpeech ikhiqiza i-spectrogram yenkulumo yonke ngokuhambisana esikhundleni sohlaka olulodwa ngesikhathi, okwenza ukuhlanganisa kusheshe kakhulu futhi kuzinze kakhudlwana.

2 min fundaFunda
Umsindo we-AI

I-NaturalSpeech kanye ne-Latent Diffusion TTS

I-NaturalSpeech iwumugqa wocwaningo lwe-Microsoft lwe-TTS oluhloselwe ikhwalithi yenkulumo yezinga lomuntu, enezinguqulo zakamuva ezisebenzisa ukusabalalisa okucashile ukuze kukhiqizwe okucebile, kwemvelo...

2 min fundaFunda
Umsindo we-AI

Ukuqashelwa Kwemizwa Yenkulumo

I-Speech Emotion Recognition (SER) yi-AI ethola isimo somzwelo sesikhulumi - intukuthelo, injabulo, ukudabuka, ukukhungatheka - ezwini lezwi laso, hhayi nje...

2 min fundaFunda
Umsindo we-AI

I-Moshi Full-Duplex Speech

I-Moshi iwumthombo ovulekile, izwi le-AI lesikhathi sangempela elivela e-Kyutai elikhuluma futhi lilalele ngesikhathi esisodwa - i-duplex egcwele - esikhundleni sokushintshana ngokuqinile.

2 min fundaFunda
Umsindo we-AI

Ukuhumusha kwenkulumo-kuya-enkulumweni

I-Speech-to-Speech Translation (S2ST) ithatha amagama akhulunywayo ngolimi olulodwa futhi ikhiqize amagama akhulunywayo ngolunye — kugcinwa kahle izwi lesikhulumi, iphimbo...

2 min fundaFunda
Umsindo we-AI

I-HiFi-GAN ne-GAN Vocoder

I-HiFi-GAN iyi-vocoder ekhiqizayo eshintsha i-mel-spectrogram ibe i-waveform yomsindo oluhlaza cishe ngaso leso sikhathi, ikhiqize inkulumo yekhwalithi yesitudiyo kude…

2 min fundaFunda
Umsindo we-AI

Ukuguqulwa kwe-Grapheme-to-Phoneme

Ukuguqulwa kwe-Grapheme-to-phoneme (G2P) kuhumusha izinhlamvu ezibhaliwe zibe imisindo uhlelo lwenkulumo okufanele luphimisele ngempela.

2 min fundaFunda
Umsindo we-AI

Ukwenziwa Kwezwi Lombhalo Kwenkulumo

Ukujwayela kombhalo isinyathelo esisekupheleni esiphinda sibhale umbhalo ongahluziwe ube amagama akhulunywa ngokuphelele ngaphambi kokuthi uhlelo lwenkulumo lusho.

2 min fundaFunda
Umsindo we-AI

I-SoundStream Neural Codec

SoundStream is Google's end-to-end neural audio codec that compresses speech and music to extremely low bitrates while preserving quality.

2 min fundaFunda

Uqedile ukufunda? Ake usikhombise sibone.

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