Ubuyobozi bwa Audio AI

UmuzikiLM: Hierarchical Semantic na Acoustic Tokens

UmuzikiLM ni __AIU_PROTECTED_11 __ 'inyandiko-yumuziki yerekana amajwi-maremare yerekana amajwi maremare binyuze murwego rwibimenyetso byerekana imiterere yumuziki hamwe nibimenyetso bya acoustic kugirango bisobanuke neza.

2 min somaIbiherutse kuvugururwa

Kwibira cyane

Byatangajwe na Google Ubushakashatsi mu ntangiriro za 2023, MusicLM ikora ibisekuruza byumuziki nko guhanura ibimenyetso byerekana amajwi atandukanye, nkurugero rwururimi ruhanura amagambo. Ikoresha urwego rwerekana: ibimenyetso byerekana (biva kuri moderi yitwa w2v-BERT) bifata imiterere yo murwego rwohejuru nka melody na rhythm hejuru yigihe kirekire, mugihe ibimenyetso bya acoustic (biva kuri codec ya SoundStream neural codec) bifata ibisobanuro byiza nka timbre nuburyo. Icyiciro cya mbere kibyara ibimenyetso biva mubisobanuro byanditse, hanyuma ibyiciro byanyuma byuzuza ibisobanuro bya acoustic bisabwa kuri ayo masomo. Gutondekanya inyandiko biva muri MuLM / MuLan, guhuriza hamwe umuziki-inyandiko ushiramo imyitozo kuburyo ibisobanuro hamwe nubutaka bwamajwi mumwanya umwe. Ubu buryo bwateguwe butuma MusicLM igumaho mumuziki muminota mike aho gutembera nyuma yamasegonda make.

Ubushishozi

Igitekerezo cyingenzi ni ugukuramo imiterere kuva muburyo butandukanye. Ikimenyetso gisobanutse neza ni gake kandi gihinduka buhoro, bityo Transformer irashobora kwerekana imiterere yigihe kirekire idafite uburebure bukurikiranye. Ibimenyetso bya Acoustic ni byinshi kandi biri hejuru cyane, ariko bigomba gusa guhanurwa byateganijwe kumasomo yamaze gukosorwa, bigatuma buri cyiciro gikurikirana. Ijwi rya Stream risigaye ryerekana umubare utanga kodegisi ya acoustic ya decoder ya nyuma ihinduka 24 kHz.

Ingaruka z'Ingamba

Kugera no kugera

Itezimbere kugerwaho binyuze mu kwandukura, kuvuga, no guhuza amajwi.

Igiciro na bije

Amatsinda yibitangazamakuru arashobora kohereza amajwi yihuse hamwe na bije nto.

Umuvuduko n'igipimo

Sisitemu ireba abakiriya irashobora gutunganya imikoranire ivugwa murwego runini.

Ejo hazaza h'umuzikiLM: Hierarchical Semantic na Acoustic Tokens

UmuzikiLM urwego rwibimenyetso byahindutse icyitegererezo cya sisitemu nyuma nka MusicGen nibikoresho byumuziki byubucuruzi. Tegereza uburyo bwiza bwo gucuranga (hum a tune, ubone gahunda yuzuye), indirimbo ndende zubatswe neza hamwe n'imirongo hamwe na korari, hamwe no kugenzura neza ibikoresho nurufunguzo. Ibibazo by'amahwa biremewe n'amategeko kandi byitwara neza: guhugura amakuru yamakuru, uruhushya rwabahanzi, hamwe no kwerekana amazi byakozwe amajwi kuburyo bishobora gutandukanywa numuziki wakozwe nabantu ubu nibyingenzi kubyohereza.

Gushyira mu bikorwa Isi

Guhindura ibisobanuro byanditse mubisobanuro bya firime cyangwa trailer, 'orchestre epic yubatswe hamwe na korari'

Gukora umuziki winyuma uteganijwe kumashusho yerekana amashusho cyangwa no gushushanya ibisobanuro byubuhanzi

Kwagura injyana ngufi cyangwa ifirimbi muburyo bwuzuye ibikoresho

Gukora ibicuruzwa bitandukanye-umuziki ukurikirana kuri tempos nuburyo butandukanye bwo kwamamaza hamwe nabakora ibintu

Ingaruka & Kurinda

Gukoresha nabi amajwi no kwigira ibyago byiyongera mugihe uruhushya rubuze.

Ukuri kurashobora kugabanuka hejuru yimvugo, imvugo, cyangwa urusaku rwibidukikije.

Amajwi yubukorikori arashobora kwibeshya kumvugo yukuri nta kirango gisobanutse.

Igishushanyo mbonera

1

Shaka uruhushya rusobanutse rwo gufata amajwi, gukoroniza, no gukoresha.

2

Ikizamini cyiza mubiganiro bitandukanye hamwe nuburyo bwimbere.

3

Sobanura igihe umuntu agomba gusuzuma cyangwa kwemeza ibisubizo.

4

Andika amajwi yubukorikori kandi ugumane inyandiko zerekana kubazwa.

Komeza Ubushakashatsi

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 MusicLM: Hierarchical Semantic and Acoustic Tokens quiz

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

Tangira ikibazo

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

Ubuyobozi bukurikira

Ibisekuruza byumuziki

Ibibazo bikunze kubazwa

What is MusicLM: Hierarchical Semantic and Acoustic Tokens?

UmuzikiLM ni __AIU_PROTECTED_11 __ 'inyandiko-yumuziki yerekana amajwi-maremare yerekana amajwi maremare binyuze murwego rwibimenyetso byerekana imiterere yumuziki hamwe nibimenyetso bya acoustic kugirango bisobanuke neza.

Nigute MusicLM ifata muburyo bwo gukora umuziki?

UmuzikiLM utegura ibisekuruza byumuziki nkubuhanuzi bwa autoregressive hejuru yerekana amajwi yihariye, bisa nuburyo moderi yururimi ruhanura amagambo.

Ni uruhe ruhare rw'ibimenyetso bisobanura muri MuzikaLM?

Ibimenyetso bya semantique (kuva kuri w2v-BERT) bifata ibintu bito, bigenda bihinduka buhoro buhoro nka melody na rhythm mugihe kirekire.

Nibihe bice bitanga ibisobanuro byiza bya acoustic nka timbre nuburyo?

Ibimenyetso bya Acoustic biva muri SoundStream neural codec kandi bigashyiraho amakuru meza nka timbre nuburyo.

Nigute MusicLM ihuza inyandiko yihuta kumajwi yumuziki?

MuLan yatojwe kugirango ibisobanuro byanditse hamwe nu ikarita yerekana amajwi ahantu hafi aho hasangiwe gushyiramo, bigahindura inyandiko.

Ni ukubera iki igishushanyo mbonera, cyateguwe gifasha imiterere ndende?

Ibimenyetso bidasanzwe bihinduka gahoro gahoro, bityo Transformer irashobora kwerekana imiterere yigihe kirekire neza mbere yuko acoustic yuzuye yuzuye.