I-Parallel WaveGAN Vocoder
I-Parallel WaveGAN iyi-vocoder ye-neural esheshayo eshintsha i-mel-spectrogram ibe i-waveform yomsindo eluhlaza isebenzisa i-GAN encane, ikhiqize wonke amasampuli ngesikhathi esisodwa.
Uhlolojikelele
It matters because it gives near-real-time, high-quality speech with a compact model.
I-Deep Dive
Ivokhoda isigaba sokugcina sepayipi le-TTS: iguqula imephu yesici se-acoustic (imvamisa i-mel-spectrogram) ibe igagasi lomsindo langempela olizwayo. I-Parallel WaveGAN, ehlongozwe u-Yamamoto, iNgoma, noKim ngo-2019, yenza lokhu ngejeneretha yesitayela se-WaveNet engalawuleki eqeqeshwe njengenethiwekhi ekhiqizayo yokuphikisana. Esikhundleni sokubikezela isampula yomsindo eyodwa ngesikhathi njenge-WaveNet yasekuqaleni, ikhiqiza lonke uhlobo lwamagagasi ngokuhambisana, ilwenza lusheshe kakhulu. Iresiphi yayo eyinhloko ihlanganisa ukulahlekelwa okuphambene nokulahlekelwa kwe-Fourier transform (STFT) yesikhathi esifushane yokuxazululwa okuningi, ngakho imodeli ifanisa isignali yangempela phakathi kwezikhathi ezimbalwa nezikali zefrikhwensi. Umphumela uba ijeneretha encane (cishe amapharamitha ayizigidi eziyi-1.4) esebenza ngokushesha izikhathi eziningi kunesikhathi sangempela ku-GPU.
I-Technical Insight
Ijeneretha iyinethiwekhi ye-dilated-convolution efakwe ku-mel-spectrogram kanye nokokufaka komsindo, umsindo wemephu kanye nezici eziqondile kumasampuli. Ukuqeqesha ngokuhlanganyela kunciphisa ukulahlekelwa kwe-STFT enezixazululo eziningi, kuhlanganiswe ngokuqhathanisa ama-spectrogram obukhulu kumasayizi amaningana e-FFT nobude be-hop, kanye nokulahlekelwa okuphikisayo okuvela kumbandlululi owahlulela iqiniso. Itemu le-STFT lizinzisa futhi lisheshise ukuqeqeshwa kwezitha, lithwebula kokubili imininingwane emihle kanye nesimo esibanzi se-spectral ngaphandle kokucwiliswa kwe-distillation.
I-Strategic Impact
Finyelela futhi ufinyelele
Ithuthukisa ukufinyeleleka ngokuloba, ukulandisa, nezixhumi ezibonakalayo zezwi.
Izindleko kanye nesabelomali
Amaqembu emidiya angathumela umsindo opholishiwe ngokushesha ngamabhajethi amancane.
Isivinini nesikali
Amasistimu abhekene nekhasimende angacubungula ukusebenzelana okukhulunyiwe ngesilinganiso esikhulu.
Ikusasa le-Parallel WaveGAN Vocoder
I-Parallel WaveGAN isize ekusunguleni ama-vocoder e-GAN njengokuzenzakalelayo okusebenzayo, futhi ukulahlekelwa kwayo kwe-STFT enezixazululo eziningi manje sekuvela kubo bonke abalandelayo njenge-HiFi-GAN nezinhlelo eziningi zokusakaza. I-trajectory ikhomba kumavokhoda amancane kakhulu, abambezeleka kancane kubasizi abakudivayisi, izinsiza zokuzwa, nokuguqulwa kwezwi bukhoma, kanye namavowuda ajwayelekile afinyelela kuzipikha ezingabonwa. Lindela ukuhlanganiswa okuqinile nge-TTS yokuphela-siya-ekugcineni kanye nokusetshenziswa okuphumelelayo kuma-chips eselula nashumekiwe.
Ukuqaliswa Komhlaba Wangempela
Okukhipha inkulumo yesikhathi sangempela kuzisizi zezwi leselula lapho ukubambezeleka nosayizi wemodeli kubalulekile
Isebenza njengejeneretha ye-waveform ebhangqwe namamodeli we-acoustic afana ne-Tacotron 2 noma i-FastSpeech
Umbhalo uye enkulumeni ekudivayisini wamathuluzi okufinyelela angakwazi ukuthembela kumafu
Amasistimu okuguqula izwi ahlanganisa kabusha ama-spectrogram aguqulelwe kumsindo ozwakalayo wemvelo
Izingozi & Guardrails
Ukusetshenziswa kabi kwezwi kanye nezingozi zokuzenza ongeyena ziyanda uma imvume ingekho.
Ukunemba kungase kwehle kuzo zonke izinhlobo zokuphimisela, izilimi zesigodi, noma izindawo ezinomsindo.
Umsindo wokwenziwa ungenziwa iphutha njengenkulumo eyiqiniso ngaphandle kokulebula okucacile.
Ukuqalisa Umhlahlandlela
Thola imvume esobala yokuthwebula izwi, ukuhlanganisa, nokusebenzisa kabusha.
Ikhwalithi yokuhlola kuzo zonke izipikha nezimo zangemuva.
Chaza ukuthi kunini lapho umuntu kufanele abuyekeze noma agunyaze okuphumayo.
Lebula umsindo wokwenziwa futhi ugcine amarekhodi atholakalayo ukuze aziphendulele.
Qhubeka Uhlole
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 Parallel WaveGAN Vocoder 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
Umhlahlandlela olandelayo
I-MelGAN Generative Vocoder
Imibuzo evame ukubuzwa
What is Parallel WaveGAN Vocoder?
I-Parallel WaveGAN iyi-vocoder ye-neural esheshayo eshintsha i-mel-spectrogram ibe i-waveform yomsindo eluhlaza isebenzisa i-GAN encane, ikhiqize wonke amasampuli ngesikhathi esisodwa. Ibalulekile ngoba inikeza inkulumo yesikhathi sangempela, yekhwalithi ephezulu enemodeli ehlangene.
Uyini umsebenzi wevokhoda njengeParallel WaveGAN?
Ivokhoda yisiteji sokugcina se-TTS esihlanganisa igagasi lomsindo langempela kusuka ezicini ze-acoustic njenge-mel-spectrogram.
I-Parallel WaveGAN iwenza kanjani amasampula omsindo uma kuqhathaniswa ne-WaveNet yoqobo?
I-Parallel WaveGAN ayisebenzi ngokuzenzakalelayo, ikhiqiza lonke uhlobo lwegagasi ngesikhathi esisodwa kunesampula ngesampula, okuyenza isheshe kakhulu.
Yikuphi ukulahlekelwa okuphakathi ne-Parallel WaveGAN ngaphandle kokulahlekelwa okuphikisile?
Ihlanganisa ukulahlekelwa okuphambene nokulahlekelwa kwe-STFT ye-multi-resolution eqhathanisa ubukhulu be-spectrogram ezikalini ezimbalwa.
Iyiphi i-architecture esetshenziswa ijeneretha ye-Parallel WaveGAN?
Ijeneretha iyinethiwekhi efana ne-WaveNet eyakhiwe kusuka kuma-convolutions anwetshiwe, afakwe kusimo se-mel-spectrogram nomsindo.
Kungani i-Parallel WaveGAN ikhanga ukuthunyelwa?
Cishe ngamapharamitha ayizigidi ezingu-1.4 incane futhi isebenza ngokushesha izikhathi eziningi kunesikhathi sangempela, ilungele ukusetshenziswa kudivayisi.