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。

Speak IPA – Text to Speech for International Phonetic Alphabet

102 点作者 bearbin超过 8 年前

18 条评论

saurik超过 8 年前
The IPA itself isn&#x27;t really sufficient to encode the sound of a word: you also need to know what language is being spoken; there is a little book you can get of vowel charts for all of the major languages in the world that tries to document the exact vocal position of each symbol. The issue is that there&#x27;s a continuum of sound that can be generated by the human vocal system, and while humans don&#x27;t want to differentiate between subtle variations while trying to talk to each other (and so you wouldn&#x27;t expect two words with massively different meanings based on some extremely subtle and difficult to hear difference), they <i>can</i> notice the difference (which is part of what causes people to have &quot;accents&quot; based on their native languages: because they are pronouncing vowels in some slightly different part of their mouth). IPA only represents the major possibilities, not the specific variants (though there are extended and increasingly complex symbols to try to provide some more accuracy, it is again a continuum and not something you can represent with a small and finite set of symbols per vowel: you&#x27;d have to start putting a couple numbers down to represent the sound ;P).<p>Sadly, I&#x27;m having a very difficult time finding a good reference for this online. I know all of this because I spent years studying graduate Linguistics at UCSB while I was trying to get a PhD in Computer Science, and I carried around that little book of per-language vowel charts for a long time ;P.<p><a href="http:&#x2F;&#x2F;www.antimoon.com&#x2F;how&#x2F;english-vowel-chart.htm" rel="nofollow">http:&#x2F;&#x2F;www.antimoon.com&#x2F;how&#x2F;english-vowel-chart.htm</a><p>&gt; For example, the average British &#x2F;æ&#x2F; is slightly more open (more like &#x2F;a&#x2F;) than the average American &#x2F;æ&#x2F;.<p>That said, I typed all of that under an expectation that it was going to work <i>really well</i>, but in practice this website sounds a lot like Dr. Sbaitso, and so the nuance of pronunciation is totally lost anyway ;P.
评论 #13516255 未加载
评论 #13514824 未加载
评论 #13515993 未加载
评论 #13515292 未加载
评论 #13516001 未加载
评论 #13516677 未加载
Mizza超过 8 年前
It&#x27;d be very, very useful if you could F&#x2F;OSS this, so that we could build something to help illustrate hard-to-pronounce Wikipedia articles, which currently have to be manually pronounced. There are thousands of these needed!
XaspR8d超过 8 年前
It&#x27;s amazing for how useful IPA is (at least at providing an reasonable fidelity intermediate form between other, more-accurate representations) how few FOSS projects I&#x27;ve seen use it.<p>Really what I&#x27;m saying is I&#x27;d like to see someone build an automated pun-discovery tool.
评论 #13518655 未加载
DonaldFisk超过 8 年前
It would be interesting to learn the approach taken when developing this.<p>I sounds clear enough, but there are a few issues which would need to be resolved before I would use it. For example, when I entered &quot;o:&quot;, which should be a long pure vowel, I got a diphthong. The first example [ˈnɑɹkoʊˌklɛpˈtɑkɹəsi] has the IPA for a General American accent but sounds more like Received Pronunciation to me. Some IPA characters aren&#x27;t voiced at all. These might be fixable, but how easy this is depends on the implementation approach.<p>Decades ago, I developed a formant speech synthesizer (the details are here: <a href="http:&#x2F;&#x2F;web.onetel.com&#x2F;~hibou&#x2F;Formant%20Speech%20Synthesizer.txt" rel="nofollow">http:&#x2F;&#x2F;web.onetel.com&#x2F;~hibou&#x2F;Formant%20Speech%20Synthesizer....</a>). Formant speech synthesizers work by passing a pulsed or random input through a series of filters to generate speech sounds, and can be easily adapted to different accents and speakers. However, it is difficult to get them to sound natural, so they usually sound more like Daleks than people.<p>I&#x27;ve also done some rule-based text to speech. This works quite well for Standard English pronunciations in a Glasgow accent, the closest accent to English spelling and therefore the one which can be most reliably generated with the smallest number of exceptions.<p>More recent approaches to speech synthesis sound more natural but are limited to a particular accent and speaker. It&#x27;s never a Glasgow accent, and developing one for a new speaker and accent is a major undertaking. Were I to switch accents to Received Pronunciation or General American, there would be many more exceptions to the pronunciation rules. Storing pronunciations in a dictionary only works for words stored in the dictionary.
delgaudm超过 8 年前
As a voice actor, I am in LOVE with this idea, and have searched for this very thing a number of times. I&#x27;m really glad to see it created. Im constantly faced with saying words I have no idea how to pronounce correctly, and I spend far too much time trawling through youtube videos, or on forvo.com, and its ilk in the hopes of finding the word correctly pronounced.<p>I wonder, though, if it&#x27;s a shortcoming of IPA that the generated pronunciations are not what I&#x27;d expect. Example, my hometown of Annapolis is here [1] by this tool: compared to how it&#x27;s actually pronounced [2]<p>[1]<a href="https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%C9%99%CB%88n%C3%A6p%C9%99l%E1%B5%BBs" rel="nofollow">https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%C9%99%CB%88n%...</a> [2]<a href="https:&#x2F;&#x2F;youtu.be&#x2F;1I71yL3SG80?t=11" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;1I71yL3SG80?t=11</a><p>As you can hear it&#x27;s pretty far off, so much so I would be unable to rely on the computer generated version.
评论 #13516874 未加载
aliceyhg超过 8 年前
This is the first time I&#x27;m hearing about IPA. I wanted to test out how IPA works so I searched for chinese to IPA converter and came across this site: <a href="http:&#x2F;&#x2F;easypronunciation.com&#x2F;en&#x2F;chinese-pinyin-phonetic-transcription-converter#result" rel="nofollow">http:&#x2F;&#x2F;easypronunciation.com&#x2F;en&#x2F;chinese-pinyin-phonetic-tran...</a><p>I put in a few chinese sentences, got the IPA, then pasted into your app and listened to the sentence in IPA. Although it wasn&#x27;t very accurate, its one of the coolest things I learned this year. Thank you very much for sharing.<p>I think a really cool next step is to add the ability to type things in and get the IPA and pronunciation.
评论 #13519154 未加载
compay超过 8 年前
I&#x27;ve been hoping to see something like this for quite some time. Kudos for a really cool project and for making it available for people to play with.<p>At least for Spanish, it can pronounce some words fairly well. I wrote a Spanish orthography-to-IPA converter a few years back. It&#x27;s up on Heroku until folks crash it if you want to get some Spanish words transcribed to IPA.<p><a href="http:&#x2F;&#x2F;spanish-demo.herokuapp.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;spanish-demo.herokuapp.com&#x2F;</a><p>I used it to generate a few random words. Some of the sounds were off - for example ɾ (the &quot;r&quot; in &quot;estar&quot;). But many words were pronounced clearly enough to be understood.
yoz-y超过 8 年前
Some time ago I&#x27;ve found out that the macOS say command does support IPA. However not all word seem to work.
brownbat超过 8 年前
I always wanted to have a text-to-speech system that could generate novel accents, by taking just a couple parts of the IPA at a time and substituting other sounds.<p>Text-to-IPA might be easy enough with dictionaries, the swapping is trivial, but IPA-to-speech seems like a harder problem.
moontear超过 8 年前
Finally some closure: Worcestershire sauce is &quot;wʊstərʃər&quot; according to <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Worcestershire_sauce" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Worcestershire_sauce</a>
评论 #13516561 未加载
AceJohnny2超过 8 年前
Hm, it didn&#x27;t deal too well with Llanfairpwllgwyngyll...<p><a href="https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%C9%ACan%CB%8Cvair+pu%C9%AC%CB%88%C9%A1w%C9%A8%CC%9En%C9%A1%C9%A8%CC%9E%C9%AC" rel="nofollow">https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%C9%ACan%CB%8C...</a><p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Llanfairpwllgwyngyll" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Llanfairpwllgwyngyll</a>
tyingq超过 8 年前
Didn&#x27;t know about IPA before seeing this, thanks for sharing.<p>Saying &quot;hacker news&quot; in IPA using your tool: <a href="https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%27h%C3%A6k%C9%99r++nuz" rel="nofollow">https:&#x2F;&#x2F;speak-ipa.bearbin.net&#x2F;speak.cgi?speak=%27h%C3%A6k%C9...</a>
fishnchips超过 8 年前
I checked a few examples from my native language (Polish) and they sound amusing at best.
orthopteroid超过 8 年前
Hey cool! I finally have somewhere on the web that will make audio for my markov syllable-synthesis engine!<p><a href="http:&#x2F;&#x2F;blurtmime.appspot.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;blurtmime.appspot.com&#x2F;</a>
carlob超过 8 年前
Doesn&#x27;t seem to work in Safari, probably because the audio is a wav.
评论 #13514800 未加载
msephton超过 8 年前
This is great, but I have to use Chrome to use it. I&#x27;d prefer to use Safari.<p>Do you plan to let Wikipedia use this? It would be really useful on their site.
amelius超过 8 年前
Back in the 80s, a friend of mine had a text-to-speech program running on a Z80 machine (I think), which sounded a lot like this.
pwdisswordfish超过 8 年前
This appears to be just a web wrapper around <a href="http:&#x2F;&#x2F;espeak.sourceforge.net&#x2F;" rel="nofollow">http:&#x2F;&#x2F;espeak.sourceforge.net&#x2F;</a>, and not a very slick one either. For one, it could use the &lt;audio&gt; element instead of forcing me to download the sound file.
评论 #13519056 未加载