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。

What makes Bach sound like Bach? New dataset teaches algorithms classical music

122 点作者 huan9huan超过 8 年前

9 条评论

savanaly超过 8 年前
The question of what makes Bach sound like Bach is, needless to say, not addressed.<p>The actual thing they&#x27;re reporting is:<p>&#x27;“You need to be able to say from 3 seconds and 50 milliseconds to 78 milliseconds, this instrument is playing an A. But that’s impractical or impossible for even an expert musician to track with that degree of accuracy.”<p>The UW research team overcame that challenge by applying a technique called dynamic time warping — which aligns similar content happening at different speeds — to classical music performances. This allowed them to synch a real performance, such as Beethoven’s ‘Serioso’ string quartet, to a synthesized version of the same piece that already contained the desired musical notations and scoring in digital form.<p>Time warping and mapping that digital scoring back onto the original performance yields the precise timing and details of individual notes that make it easier for machine learning algorithms to learn from musical data.&#x27;<p>It also mentions that they attempted to apply existing deep learning algorithms designed for speech recognition to their new dataset, hoping to be able to accomplish a task such as predict a single missing note from a long string of notes. It does not say whether this worked.
评论 #13107349 未加载
ktRolster超过 8 年前
Albert Schweitzer pointed out (in <a href="https:&#x2F;&#x2F;www.amazon.com&#x2F;dp&#x2F;0486216314" rel="nofollow">https:&#x2F;&#x2F;www.amazon.com&#x2F;dp&#x2F;0486216314</a> ) that in many cases it&#x27;s hard to understand Bach&#x27;s music without understanding the lyrics. The mood of the music will change from cheerful to somber (or whatever) seemingly randomly, but if you understand the lyrics, it&#x27;s not random.
评论 #13108056 未加载
haberman超过 8 年前
This is really interesting, but it confused me at first. Given the title and the problem posed in the article&#x27;s intro, I figured this would be a dataset of sheet music, ie. the notes and durations specified in some printed music. However, reading more it appears to be focused on recordings (ie. audio) and annotating those recordings with information about where each note starts and stops.<p>So to me this seems more directly applicable to transcription (ie. taking audio and turning it into sheet music) or synthesis (taking sheet music and turning it into audio of a human-sounding performance) than it does to composition or finishing unfinished works by famous composers. The output of the compositional process is generally sheet music, not audio, so it seems to make more sense that problems around composition would be trained and learn in the sheet music domain.<p>I&#x27;m not a machine learning researcher though! This is just my impression as a musician.
评论 #13107102 未加载
haberman超过 8 年前
This news reminded me of this gem, from back in the day (I think 1996-ish):<p><a href="http:&#x2F;&#x2F;www.markheadrick.com&#x2F;midi&#x2F;absmfaq.txt" rel="nofollow">http:&#x2F;&#x2F;www.markheadrick.com&#x2F;midi&#x2F;absmfaq.txt</a><p>In section 1.4 they very emphatically state that &quot;with current technology, IT CAN&#x27;T BE DONE.&quot;<p>They conclude: &quot;Think of it this way: If you don&#x27;t mind spending more than the US national debt on computer equipment and waiting a few years for the job to complete, you can have a system that MIGHT accurately convert the digital waveform data of a 5 minute song into a small, compact MIDI file.<p>Otherwise, you can blow a couple of thousand dollars hiring a professional band of studio musicians and engineers who can probably give you what you want in about one day.&quot;<p>It is humorous for its emphatic-ness, but also educational for being a picture into how we&#x27;ve historically thought about this problem.
pierrec超过 8 年前
This announces a new dataset where recorded performances are precisely synchronized to MIDI transcriptions. Obviously the article doesn&#x27;t seem to get the implications quite right (it&#x27;s very useful for performance-related research, not so much for AI composition).<p>As a composer, the coolest potential I see here is training a model to create realistic mockups from MIDI compositions. For that purpose, though, it would be better to start with a fully monophonic&#x2F;solo-instrument dataset, which would simplify the learning. Also, MIDI data is not entirely sufficient: annotations on dynamics and playing technique would be necessary to make a good mockup tool, since this is the kind of information one might even give to human performers.<p>Anyways, it would be tough for such a tool to catch up with current state-of-the-art, sample-based mockup tools, which are already baffling in their realism, although they usually require a lot of work to get good results. But one can always dream of a &quot;Stokowski&quot; or &quot;Karajan&quot; neural network that interprets your MIDI composition with emotion and sensibility!
mrcactu5超过 8 年前
i ran into a few issues trying to study classical music with a computer. first of all is merely putting in some representation of the musical score into a file. This was accomplished by MIDI but I am hoping for a more standard way that looks more like the notes of a score.<p>Another problem is once you have the music there&#x27;s a tremendous amount of &quot;interpretation&quot; that a musician does. the nodes may each read 1&#x2F;8 but a musician might add or subtract 1&#x2F;64 has he&#x2F;she feels is good.<p>other times the change is more mathematical 1&#x2F;8+1&#x2F;8+1&#x2F;8 might have to actually be read 1&#x2F;12+1&#x2F;12+1&#x2F;12 = 1&#x2F;4 but that is much easier to fit into a computer<p>I have said nothing of dynamics (loud&#x2F;quiet), articulation (stoccatto, slurring etc).<p>scores are available in IMSLP and other sources. but are computer files available as well?
评论 #13107513 未加载
gattilorenz超过 8 年前
It is interesting to note that in 1990 there was an expert system composed of a myriad of handmade rules that could produce Bach-like harmonizations.<p><a href="http:&#x2F;&#x2F;www.global-supercomputing.com&#x2F;people&#x2F;kemal.ebcioglu&#x2F;pdf&#x2F;Ebcioglu-JLP90.pdf" rel="nofollow">http:&#x2F;&#x2F;www.global-supercomputing.com&#x2F;people&#x2F;kemal.ebcioglu&#x2F;p...</a><p>Unfortunately I can&#x27;t seem to find the samples now, but to my (untrained) ear they sounded as Bach as the real thing.
Gaussian超过 8 年前
Professor David Cope of UCSC has done extensive work in this space, starting with his EMI algorithm. His algos + DBs have created some in incredible music in the Bach style.
lalos超过 8 年前
Relevant project to train a model that generates Bach music<p><a href="http:&#x2F;&#x2F;bachbot.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;bachbot.com&#x2F;</a>