va'o: Difference between revisions

From Lojban
Jump to navigation Jump to search
mNo edit summary
 
mNo edit summary
Line 1: Line 1:


The first step of a general speech recognition system (and the kind one would want for Lojban), consists of phoneme recognition. There are two ways of doing it (roughly?):
''va'o'' is the modal of ''vanbi'', and describes the environment in which an event takes place. This means it could sometimes translate English ''where...'' or ''while...'' However, some people have extended this sense in order to use it as a modal for "if", even though [[jbocre: bai|bai]] and [[jbocre: ja'e|ja'e]] do a better job of that.


# Some kludgy looking algorithmic process for identifying phonemes based on voice features. (Bebe (sorry, URL tomorrow) does this)
va'o was once very commonly used by people who opposed [[jbocre: ganai, gi|ganai, gi]]. I haven't seen it much anymore.


** This requires you have either a very good description of the distinguishing features of each relevent phoneme, or a bunch of bunch of phoneme recordings to work from.
Many of the arguments for ''va'o'' show up under [[jbocre: ganai, gi|ganai, gi]]. ''Actually, they're probably better considered as arguments '''against''' [[jbocre: ganai, gi|ganai, gi]].'' This argument against ''va'o'' was in the '''va'o''' section of the huge ''if'' page:


# Some kludgy method for comparing extracted voice features to the voice features of a bunch of phoneme recordings on record.
* The problem (in my opinion) with ''va'o'' is that we need a quick and easy way to say "I had fun at the performance." ''mi se zdile va'o le se tigni'' is the most obvious way to do it, but then vanbi1 must occur in this world. Therefore, I support use ''va'o'' for this and ''bai'' for ''if''. -- [[jbocre: Adam|Adam]]
** One could use ''li'i'' for this, e.g. ''leli'i se tigni cu zdile mi''...


** This requires a bunch of phoneme recordings to work from.
** ''mi se zdile le nu mi pu zvati le se tigni''
*** That's using a trick of the place structure of ''zdile''. How would you translate "I argued at the meeting."? (other than ''mi darlu va'o le nu penmi'')


# Other?
*** ''mi pu darlu co gridikni''. Generally, ''broda brode'' or ''broda me le sumti'' can be used to convey this information.
**** There's always another way to say something. When someone suggests a certain usage, they are most likely not implying that there is some concept which would be absolutely impossible to express without it. However, it might be more convenient, or more clear. --[[jbocre: rab.spir|rab.spir]]


** This requires that you replace "Other?" with a description. :)
* In some cases, ''[[jbocre: if|if]]'' in English refers to something like "environment". For example:
** ''Have some coffee if you want.''


So, does anyone happen to have any idea where to get a lot of phoneme recordings, with the phoneme boundries convinently premarked? Or descriptions of algorithms for identifying phonemes (without recordings to match again)? The Lojban speech synthesis data for festvox/festival would be nice, but when I looked earlier today, the URLs for it were broken, and the whole webserver seemed fairly mucked up.
*** ''.einai .e'a ko pinxe lo ckafi''
*** ''.e'u do pinxe lo'e ckafi va'o le nu do djica co no'a''


* Why doesn't someone organize a research project, by getting a bunch of lojbanists to pronounce every phoneme, and then analyzing the differences and similarities between them, until we can at least begin to nail down what makes these sounds different. -- mi'e [[jbocre: bancus|bancus]]
*** This doesn't seem like an example of an environment, but a motivation: ''mu'ida'i''
** because there are already huge corpora of sounds out there, which are already tagged so that you know exactly where every last phoneme in the corpus starts and stops. see the [http://www.ldc.upenn.edu/ inguistic Data Consortium]. problem is they only distribute on CD, and the CDs are usually $100 or so a pop. and i, at least, have zero interest in trying to tag hundreds of thousands of phonemes. i've found decent corpora floating about freely on the internet in the past, but they didn't have phoneme boundries tagged. --[[jbocre: Jay Kominek|Jay]]
 
** Just a piece of technicality about terminology (never a Loglan/Lojban strong point): you cant have a recording of ''phonemes'' as such, only of ''phones''. A phoneme is a language-specific grouping of phones -- actually produced sounds -- that are taken as functioning as identicals in a given language. So what we want is either a way of dividing up phones into phonemes of Lojban or a way of generalizing from various phones taken in Lojban to belong to the same phoneme. >|8}

Revision as of 17:18, 4 November 2013

va'o is the modal of vanbi, and describes the environment in which an event takes place. This means it could sometimes translate English where... or while... However, some people have extended this sense in order to use it as a modal for "if", even though bai and ja'e do a better job of that.

va'o was once very commonly used by people who opposed ganai, gi. I haven't seen it much anymore.

Many of the arguments for va'o show up under ganai, gi. Actually, they're probably better considered as arguments against ganai, gi. This argument against va'o was in the va'o section of the huge if page:

  • The problem (in my opinion) with va'o is that we need a quick and easy way to say "I had fun at the performance." mi se zdile va'o le se tigni is the most obvious way to do it, but then vanbi1 must occur in this world. Therefore, I support use va'o for this and bai for if. -- Adam
    • One could use li'i for this, e.g. leli'i se tigni cu zdile mi...
    • mi se zdile le nu mi pu zvati le se tigni
      • That's using a trick of the place structure of zdile. How would you translate "I argued at the meeting."? (other than mi darlu va'o le nu penmi)
      • mi pu darlu co gridikni. Generally, broda brode or broda me le sumti can be used to convey this information.
        • There's always another way to say something. When someone suggests a certain usage, they are most likely not implying that there is some concept which would be absolutely impossible to express without it. However, it might be more convenient, or more clear. --rab.spir
  • In some cases, if in English refers to something like "environment". For example:
    • Have some coffee if you want.
      • .einai .e'a ko pinxe lo ckafi
      • .e'u do pinxe lo'e ckafi va'o le nu do djica co no'a
      • This doesn't seem like an example of an environment, but a motivation: mu'ida'i