Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

If we are voting on missing letters I want thorn(þ). My understanding is that thorn is one of the rarer sounds in the worlds languages, and it deserves to get it's own letter back.

On the topic of screwball spelling is this video essay on silent letters. The fun takeaway for me was that a lot of silent letters were never pronounced. it is just that when some of the first dictionaries were being produced, and the spellings decided on, they decided to introduce silent letters to indicate the origin of the word. the b in debt is because it comes from the latin debitum. but it was not spelled that way until the 1500's prior to that it was dette.

https://www.youtube.com/watch?v=NXVqZpHY5R8 (RobWords: Why English is full of silent letters)



It would be nice to revive all of the Old English letters (well, except for the wynn Ƿ because it's so easily confused with P).

"æ" even has the same obvious sound value still, it can even keep the name "ash"

"þ" and "ð" for the two th-sounds (the former unvoiced, the latter voiced).

And if "ᵹ" is readmitted specifically in its affricate capacity, i.e. for "g" in "gem" etc, then "j" could instead be used with the value it has in French, i.e. used to spell words like "measure" - this is one of the few English phonemes that doesn't have a definitive letter associated with it right now.

Always use "k" for that sound and repurpose c/q/x for something else, and we could ditch the digraphs completely.


I don't know how many of you need to read this but no one is stopping you from doing any of this. Putting aside cultural friction and being thought a bunch of quacks, you could just start doing these things. There's no real authority telling anyone that they can't despite what some people believe. Just do it!


Exactly. What are we, French?!



And if "ᵹ" is readmitted specifically in its affricate capacity, i.e. for "g" in "gem" etc

I'm in. It would also clear up some ambiguity over the pronunciation of "gif" ;-)


There is no ambiguity in the pronunciation of "GIF". The "g" is pronounced just like the the "g" in "garage".


It's in quantum superposition. Actually speaking it collapses the wavefunction around that particular speaker, although some prefer to believe instead that reality forks. ~


omg. fell down laughing. perfect comment



Pronounce the g in garage


Not like the g in jraphics then? :D


I'm more interested in the pronunciation of "jpeg"... you're all saying jay-pezh properly, aren't you?


By the "g as in graphics" logic for "gif", for "jpeg" we have "j as in joint", "p as in photographic", "e as in experts", and "g as in group", so "je-feck"?


It's pronounced gee-pejh.

"J as in jif"-p-e-"g as in gif"

Get it right you people!


i am inclined to agree on all points, and while the second parenthetical would be useful in Contemporary English, i cannot help but note that "þ" and "ð" in Old English both represented the same phoneme (unlike in, say, Icelandic). all of the OE fricatives (/s/, /f/, /þ/) had predictable phonetic voicing depending on environment (voiced intervocalically, unvoiced elsewhere), but no phonemic distinction. in extant MSS, <þ> and <ð> are completely interchangable, mere stylistic variants of writing the phoneme, and even texts written by a single scribe will often have the same word written with both letters. some older MSS will use a plain <d> for the voiced sound (and a plain <b> for the voiced /f/). i've seen at least one MS that used <th>. in Latinized versions of OE names, it's not uncommon to see <th> or <d>, but Classical OE spelling didn't generally distinguish the voiced or unvoiced.

even in Contemporary OE, there are very few minimal pairs between /þ/ and /ð/ ("thigh" vs. "thy" comes to mind, but not much else apart from rare noun/verb combos like "loath" vs. "loathe"). it could be argued that we don't really need both, but the (surely obvious by now) pedant in me desires both. saying "boð" rather than "boþ" doesn't strictly change the meaning, and is not likely to cause confusion, but it sure sounds off!


Well, we get those two letters "for free" anyway, and the phonemes are distinct in modern English, so let's use them!

"ð" also has the nice property of being sufficiently similar in looks to "d" that someone reading it and not familiar with the letter might pronounce it as "d" and thereby make a decent approximation. Unfortunately that's not the case with "þ" though. If we ignored the historical letters and instead just picked something reasonably sensible, I'd probably go with "đ" and "ŧ" for this reason.


i've had people mistake "ð" for an "o" with a diacritic, but presumably that's a typeface problem. whatever we choose, i insist that we drop the names and call them "eþþ" and "ðee", by analogy with our other fricatives ;)


It would be good to see the old english letters brought in. I particularly enjoy thorn.


The voiceless alveolar lateral fricative[1] is another fun one. The only european languages that have it are Welsh and Icelandic where it's simply written "ll" and "hl". In some medieval texts it had a dedicated letter "Ỻ" or "ỻ".

[1]: https://en.wikipedia.org/wiki/Voiceless_dental_and_alveolar_...


It also occurs in Southern African languages, e.g. in the place name Hluhluwe, in KwaZulu.


Here's a fun thing you can do with AI, here ChatGPT:

"I speak a number of languages, but I'm not a linguist. How could I get a list of sounds that aren't included in the languages I speak? Would be interesting to hear what sounds I'm not used to hearing"

<Long blurb about what a great idea I had, and an intro to how to do it>

If you’d like, you could just tell me the languages you speak, and I can give you a first-pass list of major sound types you’re probably missing (like clicks, ejectives, tones, pharyngeals, etc.).

Would you like me to sketch a concrete example with your languages?

"Sure, here's my list: <my list>"

And then it gives a list of sounds you know, and sounds you don't. Pretty cool. It even has links to a sound map site so you can hear them.

If you like, I could generate a concrete list of IPA symbols that are not in <my list> — a sort of “negative phoneme inventory”. Would you like me to build that for you?

"Yes please. Also what additional language would cover the most ground?"

One language that covers the most new ground

Amharic (Ethiopian Semitic) is a superb single add-on because it gives you, in one go: • Ejectives (tʼ, kʼ, qʼ, sʼ/tsʼ), • Pharyngeal consonants (ħ, ʕ), • Uvular stop (q), and • True gemination (contrastive long consonants).

If you want a two-language combo to “max out” the world’s rarities, add Zulu (or Xhosa) for clicks alongside Amharic.


I don't think Amharic has a uvular ejective /q'/, nor the uvular stop or pharyngeal consonants.



LOL, total hallucination?


About silent letters, French did the same, but one of the unintended consequences was to change pronunciation of many words when reading became common in the XIXth century. For instance "admirer, admiration" had a silent d before ~1830, which is now pronounced by everyone. Ditto the "ir" termination of verbs, the "r" was silent, that's why old songs have strange rhymes such as "Compère Guilleri" rhyming with "te lairas-tu mourir", and "les lilas sont fleuris" rhyming with "qu'il fait bon dormir".


And the r ending verbs like "parler" is still silent.


> one of the rarer sounds in the worlds languages

Is that true? Seems like it's in every other word when I visit Spain...


This is just a feature of Castilian Spanish: https://en.wikipedia.org/wiki/Phonological_history_of_Spanis... \th\ only occurs naturally in like 5% of the thousands of human languages that have ever existed. Just because those languages are some of the most widely-spoken ones worldwide does not make the sound a commonly-occurring one in a meaningful phonological sense.


I know Japanese does not have a th sound, and I don't think chinese or most other asian languages have it, but am less sure about that. Unfortunately I lack the data needed to substantiate my claim.

    with
    lang_sounds as (
    select
        lang,
        unnest(string_to_array(ipa, null) ) as sound
    from world_dictionary
    ),
    totals as (
    select
        lang,
        count(sound) as sound_count
    from lang_sounds
    group by lang
    )

    select
        lang,
        totals.sound,
        count(sound) / totals.sound_count
    from
        lang_sounds join
        totals on
        lang_sounds.lang = totals.lang
    where sound = 'θ' or sound = 'ð' or sound = 'θ̠' or sound = 'z'
    group by lang, sound
    order by count(sound) / totals.sound_count


https://phoible.org/parameters has the data you seek: 5% of languages in the database have eth (ð) and 4% have theta (θ). Z is not a 'th' sound and fairly common at 30% of languages, though.


> I know Japanese does not have a th sound, and I don't think chinese or most other asian languages have it, [...]

There's no single th sound in English. There's a few different sounds you get from that letter combination in different words (and in different dialects).


Out of all Asian languages (East and South East) I can think of, only Burmese has ð and θ.


It’s true. English and the main Spain version of Spanish are two of the few languages in the world which have the sound. Even most Latin American versions of Spanish (maybe all?) do not have it.


Can you give an example of a common Spanish word that has it?


In "distinción" spanish, the classic pair is the word for house and for hunt - "casa" and "caza" respectively. If you pronounce them the same (with an S sound), you're a Seseo speaker like (most) latin america. If you pronounce them with different sounds, one an S sound, the other a TH sound, you're a "distinción" speaker, and if you pronounce them both with a TH sound, it's the more uncommon ceceo accent, usually largely Andalusian.


Any c+e/i (cena, cine) or z+a/o/u (zarza, zorro, zurrar) is a good heuristic.

c+a/o/u sounds like k (casa, cosa, cuchara) and z+e/i does not exist.


Z+e/i does exist, but it is not very common. A few examples:

- Words that are only written with Z: zepelín, zigurat, zigzag.

- Words that can be written with either Z or C: zénit, zinc, zirconio, azimut.


I stand corrected. All of those seem loanwords, but you are absolutely right.

My main point is that if you hear the sounds "th" (za) with e or i 99% it is cena or circo and will not be zena or zirco. It is an heuristic but very reliable.

P.S. Or pececín, as a random example :P


You are right, and yes, my nickname is an intentional misspelling from the old cybercafe days when I was a silly teenager trying to look cool xD


My favourite word to troll people who are learning the language is "cerrojo" /θe'roxo/, meaning "latch" or "lock", as it contains the three most difficult consonants in the language in sequence xD


In Polish there is 'szczoteczka', which took me just about forever to learn how to pronounce. I just could not hear what I was doing wrong.


Same word in Russian is "щёточка". The lengths to which Poles are willing to go instead of just using Cyrillic will never stop to amuse me :D


I struggled quite a bit with "существительное" when learning Russian.


I was talking about spelling. I can clearly see how these clusters of consonants characteristic of all Slavic languages can be a pain for a beginner, no matter how you spell them.


No Cyrillic imports, thank you. Russia decided to be the bully and murderer of its closest neighbors, don't need any more russian influence, even if literally just on paper. The further one is from them the more safety and prosperity there is, in every possible way.


Dude, this is a linguistics thread. Ukrainian also uses Cyrillic, btw


And Cyrillic is, if anything, Bulgarian originally.


What I found helpful in parsing those z combinations is just replacing them with h instead. for example, if you went up to a random monolingual English speaker and showed them "shchotechka" they could probably pronounce it reasonably well. All those z's just throw people off.


With Polish it may be even harder to go backwards, look for a clip from "Jak rozpętałem drugą wojnę światową" movie on Youtube.


Since we're piling on with hard to say words: Danes love to ask people to say "rødgrød med fløde".

https://translate.google.com/?sl=da&tl=en&text=rødgrød%20med...

(click the speak icon)


cien


> My understanding is that thorn is one of the rarer sounds in the worlds languages,

Not as rare as the lateral fricative, the "ll" in Welsh and "hl" in Southern African languages. e.g. in the place names Llandudno in Wales and Hluhluwe in KwaZulu.

And then there's the clicks in Southern African languages. Which are usually written as a Q not followed by a u. e.g. in the place name Gqeberha or the Mbaqanga music style.


> And then there's the clicks in Southern African languages. Which are usually written as a Q not followed by a u. e.g. in the place name Gqeberha or the Mbaqanga music style.

<q> is only one of the clicks in Bantu languages! The letters <c> and <x> are used for other kinds of clicks too (for dental and lateral clicks, respectively).

And then of course there are the Khoisan languages, which use a completely different set of click letters: <ʘ ǀ ǁ ǃ ǂ>.


True. It was remiss of me to not mention the <x> click in the Xhosa language.

It's literally in the name.


> the b in debt

English speaking Swedes often transform this silent b into a spoken p which is about as awkward a result as you're imagining.


I work for a small remote company with employees all over Europe; it's pretty common for most non-native English speakers to pronounce it this way. Especially noticeable with Germans.


Interesting; I don't recall hearing it pronounced like that from my Polish colleagues, so perhaps it's something about the Germanic languages specifically?


You'd have to be a pretty mean native English speaker to judge people on how they pronounce silent letters


Who's judging? I'll save that for when my Swedish är lite mindre dålig! It's just a little strange that the "b" somehow transforms into a "p" when "b" is a perfectly common letter in Swedish. If they just pronounced the "b" I wouldn't have thought it at all notable.


Quite the contrary. I live in Germany, for the most part they're pretty thankful, just as I am when they correct my German.


Anyone correcting my Swedish is in a target rich environment!


Lots of Germans do this too, in my experience.


Made me think of this SMBC comic[1], where there's a debate if being in English or Spanish, each with around a billion speakers, makes it rare or not.

[1] https://www.smbc-comics.com/comic/phonemes


It depends on whether you define "rare" in terms of language variety or human variety, obviously. In terms of languages, it is a relatively rare phoneme. It occurs more often as an allophone of other phonemes, but in that case the speakers may not be able to distinguish it and will struggle to reproduce it in "unusual" environments.


Isn’t “þ” used in Icelandic? So it’s not completely gone at least.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: