Posted by Mark Liberman

https://languagelog.ldc.upenn.edu/nll/?p=71276&utm_source=rss&utm_medium=rss&utm_campaign=a-simple-way-to-model-prosody-in-reading

https://languagelog.ldc.upenn.edu/nll/?p=71276

In "Reading Instruction in the mid 19th century" (8/15/2025), I noted a suggestion, due to Ran Liu of Amira Learning, that a computational analysis of prosodic features could be an effective way to evaluate how well grade-school students understand what they're reading. Beyond that, Maryellen MacDonald has suggested that phrasal prosody can be seen as the phase-level analog of phonemic blending (i.e. putting the sounds of 'c' 'a' 't' together into "cat") — which might help to explain the benefits of McGuffey-style elocution lessons.

Both ideas raise the question of how to evaluate the prosody of a given student's reading. And there's a simple and obvious way to do this, described and exemplified below.

We might rely on a model that predicts duration, vocal effort, pitch, and pausing from the phonology, syntax, semantics, and pragmatics of a phrase — there's an enormous literature aiming to do this analytically — or we could rely on a modern-style end-to-end deep learning system that simply maps character sequences onto predicted acoustics.

But that's going to be complicated, either way, and there's a simpler way to start.

For decades, we've had technology that does a good job of "forced alignment", i.e. aligning speech signals with various levels of symbol-sequences representing them (see e.g. Talkin and Wightman 1994; Fox 2006;  Yuan and Liberman 2008). So from a sample of model readings for a given passage, we can derive a distribution of relevant acoustic measures, and compare the same measures derived from the performance to be evaluated.

I'll illustrate this with a simple example from the Speech Accent Archive at George Mason University, in which a large number speakers read an "elicitation paragraph":

Please call Stella. Ask her to bring these things with her from the store: Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob. We also need a small plastic snake and a big toy frog for the kids. She can scoop these things into three red bags, and we will go meet her Wednesday at the train station.

Many of the readers are native speakers of various varieties of English, e.g.

And many others are speakers of other languages — a large fraction of whom are not entirely fluent as readers of English, e.g. this native Russian speaker:

There are many issues with that last reading, but let's start with something simple, which also applies to U.S. learners of whatever language background — the location and duration of silent pauses.

The second phrase of the elicitation paragraph is a good example. The durations of the Russian speaker's inter-word pauses in milliseconds, as measured by forced alignment, are given below between curly braces in the transcript below:

Ask her to bring {240} these {520} things with her from the {290} store

In contrast, none of three sample native-English readers above have any within-phrase silent pauses. And their speech rate is also obviously faster:

There's plenty more to say about the pronunciation variation involved — and the Speech Accent Archive (at least at the time that I downloaded it) has 659 native-English readings to compare, along with even more non-native readings.

The four examples above were literally chosen at random. But I've made a systematic comparison of timing and pausing in all the native-English readers, and a large sample of non-native readers, and the pattern holds pretty well, except for a subset of highly fluent non-native readers. In a sample of learner-data from Amira Learning (one of Penn's partners in the U-GAIN project), the effects seem even stronger. (The process of getting consent to share (some of) that data is still underway…)

Accent comparison is an issue for U-GAIN as well. But this morning's goal is just to indicate an obvious and easy road towards evaluation of student reading fluency, on which the first step is simply a comparison of silent pause locations and durations.

My current guess is that 5 or 10 model readings of each passage will be plenty for that task, but time will tell.

https://languagelog.ldc.upenn.edu/nll/?p=71276&utm_source=rss&utm_medium=rss&utm_campaign=a-simple-way-to-model-prosody-in-reading

https://languagelog.ldc.upenn.edu/nll/?p=71276

Posted by Victor Mair

https://languagelog.ldc.upenn.edu/nll/?p=71253&utm_source=rss&utm_medium=rss&utm_campaign=in-which-would-be-modernizing-language-does-eskimo-mean-ice-cream

https://languagelog.ldc.upenn.edu/nll/?p=71253

Kim Jong-Un has a mission to eliminate bourgeois, foreign, and southern terminology. This story in the Daily Mail by Sabrina Penty, citing the Daily NK, is hardly scholarly, but it gives some examples, and there are other stories online. The Metro in the UK reported that "I love you" (discovered in a love letter during a routine Big-Brother check by the Socialist Patriotic Youth League) was subject to severe state criticism. "Hamburger" has to be called something else (dajin-gogi gyeopppang [double bread with ground beef]) in Korean. "Karaoke" is too Japanese (try "on-screen accompaniment machines" instead). But the most interesting ban was on the phrase "ice cream" ("aiseukeurim 아이스크림). Kim wants it replaced by eseukimo. But doesn't this show that the dear leader is weak on etymology?  Isn't it transparently a Koreanized borrowing of English eskimo?  

"Eskimo" raises all sorts of questions:

Attested since 1584, from French Esquimau, ultimately from an Old Montagnais term. Ives Goddard's theory, accepted by most linguists today, is that it derives from Montagnais ayaškimew (“snowshoe-netter”). An older theory, defended by John Steckley due to its greater acceptance in Native oral traditions, but discredited^[3] by linguists, is that it derives from a term meaning "eater(s) of raw meat".

(Wiktionary)

Usage Note: Eskimo has long been criticized as an offensive term, and many Americans either avoid it or feel uncomfortable using it. In Canada, where Eskimo is especially frowned on, the only acceptable term is Inuit, and Americans have generally come to prefer this name too, knowing it to be a term of ethnic pride. But it is not always understood that Inuit cannot substitute for Eskimo in all cases, being restricted in proper usage to the Inuit-speaking peoples of Arctic Canada and parts of Greenland. In southwest Alaska and Arctic Siberia, where Inuit is not spoken, the comparable term is Yupik, which has not gained as wide a currency in English as Inuit. While use of these more specific terms is generally preferable when speaking of the appropriate linguistic group, none of them can be used of the Eskimoan peoples as a whole; the only inclusive term remains Eskimo. · The claim that Eskimo is offensive is often supported by citing a popular etymology tracing its origin to an Abenaki word meaning "eaters of raw meat." Though modern linguists speculate that the term may actually derive from a Montagnais word referring to the manner of lacing a snowshoe, the matter remains undecided, and meanwhile many English speakers have learned to perceive Eskimo as a derogatory term invented by outsiders in scornful reference to their neighbors' eating habits. See Usage Note at Inuit.

(American Heritage Dictionary 5th ed.)

See also Wikipedia for extensive notes on "eskimo" as an exonym, recent theories about its etymology, and examples of its usage,

One thing is certain, eseukimo. doesn't mean "ice cream", except in the dear leader's febrile mind.

Selected readings

• "In North Korea, it's a dire crime to speak like a South Korean, part 2" (7/3/23)
• "In North Korea, it's a dire crime to speak like a South Korean" (4/21/23)
• "Hockey language divergence between North Korea and South Korea" (2/11/18)
• "Some remarks from North Korea on language" (Pinyin News [12/13/07])
• "Ban loan words, says North Korea" (Pinyin News [12/19/08])
• "'Bad' borrowings in North Korean" (12/3/16)
• "Is Korean diverging into two languages?" (11/6/14)
• "Is Korean diverging into two languages?, part 2" (5/4/22)

https://languagelog.ldc.upenn.edu/nll/?p=71253&utm_source=rss&utm_medium=rss&utm_campaign=in-which-would-be-modernizing-language-does-eskimo-mean-ice-cream

https://languagelog.ldc.upenn.edu/nll/?p=71253