TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Noise2Music: Generating Music from Text Using Diffusion Models

72 点作者 georgehill超过 2 年前

9 条评论

jay-anderson超过 2 年前
I'd like to see something like this used to generate an instrument from text. I don't think the 30 second clips are passable quite yet (I do like the simlish-esque vocals though). But I could see this being able to generate wavetables (or other synthesis methods). Generating an instrument from a text description would be very neat. "scratchy violin", "distorted kazoo", "combo violin and slide whistle", etc. It could be an interesting starting point to play with.
评论 #34567575 未加载
nighthawk454超过 2 年前
Pretty similar to Google Research&#x27;s recent MusicLM:<p><a href="https:&#x2F;&#x2F;google-research.github.io&#x2F;seanet&#x2F;musiclm&#x2F;examples&#x2F;" rel="nofollow">https:&#x2F;&#x2F;google-research.github.io&#x2F;seanet&#x2F;musiclm&#x2F;examples&#x2F;</a>
评论 #34567511 未加载
Hydraulix989超过 2 年前
&quot;AI plagiarism&quot; spotted.<p>The Spectrogram Model for #23 prompt &quot;It sounds energetic and like something you would hear in clubs.&quot; sounds almost EXACTLY like &quot;Psy - Gangnam Style&quot;...<p>The model is hallucinating what it was trained on.
评论 #34567559 未加载
评论 #34567447 未加载
评论 #34567232 未加载
评论 #34633718 未加载
GaggiX超过 2 年前
The clips are really good but I cannot find anything online about this model, only this page, so I wonder where this link came from.
评论 #34565372 未加载
armchairhacker超过 2 年前
Unless I missed any this sounds a lot more realistic than existing music-generating models. It&#x27;s downsampled and can&#x27;t do lyrics (just vocalizations) but the samples are passable for some muffled song you would hear in the background (e.g. from a passing car)
epistemer超过 2 年前
More artificial Muzak generation that absolutely no one will ever listen to.<p>My fav is the &quot;hippie coffee shop&quot; jam band clip. That will surely corner the market for Jam band background Muzak at &quot;hippie coffee shops&quot;. Total available market of like $5.<p>At best this new synthesis technique will be an Autechre album.
cwmoore超过 2 年前
&gt; 28 The snare is struck at every third count.<p>I don&#x27;t exactly know how to interpret this prompt, and the resulting solo drums meander around as though they don&#x27;t either. Not really on threes or waltz or 1&#x2F;3 notes, but a brief tour through all of these and other rhythms.
8jy89hui超过 2 年前
On my phone (iOS) I can’t seem to get any of the samples to play.
评论 #34567823 未加载
kleer001超过 2 年前
I call BS. Unless there&#x27;s more data to be had.
评论 #34566649 未加载