Category Archives: Linguistics

Photoshop for Voice

Source: Arstechnica, Nov 2016

Adobe has demonstrated tech that lets you edit recorded speech so that you can alter what that person said or create an entirely new sentence from their voice. It seems inevitable that it will eventually be referred to as “photoshop but for audio.”

VoCo lets you copy and paste existing words...
Enlarge / VoCo lets you copy and paste existing words…

The tech, dubbed VoCo (voice conversion), presents the user with a text box. Initially the text box shows the spoken content of the audio clip. You can then move the words around, delete fragments, or type in entirely new words. When you type in a new word, there’s a small pause while the word is constructed—then you can press play and listen to the new clip.

VoCo works by ingesting a large amount of voice data (about 20 minutes right now, but that’ll be improved), breaking it down into phonemes (each of the distinct sounds that make up a spoken language), and then attempting to create a voice model of the speaker—presumably stuff like cadence, stresses, quirks, etc., but Adobe hasn’t provided much detail yet.

... or just write whole new words.
Enlarge / … or just write whole new words.

Then, when you edit someone’s speech, VoCo either finds that word somewhere within the 20-minute clip—or if the word hasn’t been uttered, it is constructed out of raw phonemes. At around the 4:30 mark in the video you can hear the phase “three times” being constructed from scratch; if you listen carefully, it does sound a bit synthetic, but it’s not awful. Copying and pasting existing words sounds better.

Advertisements

King – Man + Woman = Queen

Source: MIT Technology Review blog, Sep 2015

Computational linguistics has dramatically changed the way researchers study and understand language. The ability to number-crunch huge amounts of words for the first time has led to entirely new ways of thinking about words and their relationship to one another.

This number-crunching shows exactly how often a word appears close to other words, an important factor in how they are used. So the word Olympics might appear close to words like running, jumping, and throwing but less often next to words like electron or stegosaurus.  This set of relationships can be thought of as a multidimensional vector that describes how the word Olympics is used within a language, which itself can be thought of as a vector space.  

And therein lies this massive change. This new approach allows languages to be treated like vector spaces with precise mathematical properties. Now the study of language is becoming a problem of vector space mathematics.

Today, Timothy Baldwin at the University of Melbourne in Australia and a few pals explore one of the curious mathematical properties of this vector space: that adding and subtracting vectors produces another vector in the same space.

… a vector relationship that appear in English generally also works in Spanish, German, Vietnamese, and indeed all languages.

 

Tom Swifty

Source: Wikipedia, date indeterminate

A Tom Swifty (or Tom Swiftie) is a phrase in which a quoted sentence is linked by a pun to the manner in which it is attributed.

Examples

  • “I’ll have a martini,” said Tom, drily (dryly).
  • “Who left the toilet seat down?” Tom asked peevishly.
  • “Pass me the shellfish,” said Tom crabbily.
  • “That’s the last time I’ll stick my arm in a lion’s mouth,” the lion-tamer said off-handedly.
  • “Can I go looking for the Grail again?” Tom requested.
  • “I unclogged the drain with a vacuum cleaner,” said Tom succinctly.
  • “I might as well be dead,” Tom croaked.
  • “We just struck oil!” Tom gushed.
  • “It’s freezing,” Tom muttered icily.
  • “They had to amputate them both at the ankles,” said Tom defeatedly.
  • “I wonder if this radium is radioactive?” asked Marie curiously.
  • “The Battle of the Nile? A lot of fun!” said Lord Nelson disarmingly.
  • “Hurry up and get to the back of the ship!” Tom said sternly.
  • “We could have made a fortune canning pineapples,” Tom groaned dolefully.
  • “I wish I drove a Scandinavian car,” Tom sobbed (Saabed).
  • “Careful with that chainsaw,” Tom said offhandedly.
  • “I’m here,” Tom said presently.
  • “Happy Birthday,” Tom said presently.
  • “Walk this way,” Tom said stridently.
  • “I stole the gold,” Tom confessed guiltily (giltily).
  • “Bingo,” Tom exclaimed winningly.
  • “Where did all the carpet on the steps go?” asked Tom with a blank stare (stair).
  • “I used to be a criminal pilot,” he ex-plained con-descendingly.
  • “I have no flowers,” Tom said lackadaisically.
  • “I know not which groceries to purchase,” Tom said listlessly.
  • “I decided to come back to the group,” Tom rejoined.
  • “Did you say to zip up my sleeping bag or the door?” Tom asked inattentively.
  • “This pizza place is great!” Tom exclaimed saucily.
  • “I dropped my toothpaste,” Tom said crestfallenly.

Related resource: Fun with Words, date indeterminate