[Simon]

There are various ways, such as these scripts, but this is beyond what is expected for the Speech Processing assignment. You should be able to find all types of errors by hand-crafting relatively short and simple test sentences.

[Simon]

No – if a word is in the dictionary then Festival will always use that in preference to G2P. This is true even if there is no dictionary entry with the required POS: it will then ignore POS and pick another entry.

[Simon]

The best way to understand the phone set is to look up common words that you know. See also this topic.

The determine the correct pronunciation for a word not in the dictionary, a good technique is to look up similar-sounding words and assemble a pronunciation from parts of them. For example, to work out the pronunciation of “Simonification” (a word I just made up, but a plausible word in English), I would use lex.lookup_all to ensure I am only retrieving dictionary entries and not using G2P:

festival>  (lex.lookup_all "Simon")
(("simon" nnp (((s ae) 1) ((m @ n) 0))))

festival>  (lex.lookup_all "magnify")
(("magnify" vb (((m a g) 1) ((n i) 0) ((f ae) 0)))
 ("magnify" vbp (((m a g) 1) ((n i) 0) ((f ae) 0))))

festival>  (lex.lookup_all "classification")
(("classification" nn  (((k l a s) 2) ((i) 0) ((f i) 0) ((k ei) 1) ((sh n!) 0))))

from which I would decide that “Simonification” might be pronounced as

s ae m @ n i f i k ei sh n!

I could optionally refine that by thinking about syllabification or syllable stress (perhaps “Simonification” should have stress on the second syllable so the vowel should be full, not reduced to schwa @).

I could also compare this to what the G2P model predicts:

festival>  (lex.lookup "Simonification")              
("Simonification" nil (((s ae m) 0) ((oo n) 0) ((i f) 0) ((i k) 0) ((ei sh n!) 0)))

In this case, the prediction looks reasonable.

[Simon]

You can simply use lex.lookup_all which shows you all available entries in the lexicon for a word:

festival> (lex.lookup_all "content")
(("content" jj (((k @ n) 0) ((t e n ?) 1)))
 ("content" nn (((k oo n) 1) ((t e n ?) 0)))
 ("content" vb (((k @ n) 0) ((t e n ?) 1)))
 ("content" vbp (((k @ n) 0) ((t e n ?) 1))))

[Simon]

I’m investigating why the exam has not yet been scheduled. It will be within that exam period.

[Simon]

Instead of suspending, try actually rebooting (might be called restart in the VMWare menus). This is equivalent to powering the machine off and on again.

[Simon]

You’re getting an error for every command you run in Festival, because you’re not using valid Scheme syntax. The commands should be wrapped in parentheses, just like in the instructions or the mentioned post.

[Simon]

This error is simply because you’re using the wrong version of Festival.

[Simon]

Post the exact command you are using to edit .bashrc.

[Simon]

Post the exact commands and error messages (preferably cut-and-paste text, rather than use screenshot) for us to diagnose this. Try these commands and see if your output is similar. Post your output here.

$ cd 
$ pwd
/home/atlab
$ ls -l .bashrc 
-rw-r--r-- 1 atlab atlab 311 Oct 18 19:22 .bashrc
$ cd Documents/sp/assignment1/
$ ls -l config.scm 
-rw-rw-r-- 1 atlab atlab 1257 Oct  9 18:04 config.scm

(assuming you placed your config.scm in that directory)

[Simon]

The vowel and consonant charts on Wikipedia have audio, which you can download and inspect in Praat, where you can of course inspect the waveform, spectrum and spectrogram.

Try Seeing Speech too.

[Simon]

If sounds works in the VM (e.g., you can play a video from speech.zone), then try this to solve an audio issue affecting Festival on some computers.

[Simon]

Yes, harmonics originate in the physical behaviour of the vocal folds. They are real, not just a concept. Of course, they are much, much easier to see and understand in the frequency domain than in the time domain.

You are trying to find the origin of harmonics in the time-domain, which is a good idea, but is never going to be simple. I think the place to start is to convince yourself that any periodic signal that is not a pure tone must have harmonics. This tool is my favourite.

A guitar string, the Millennium Bridge, or (even more spectacularly) the Tacoma Narrows Bridge, all exhibit resonance. In other words, they are filters that selectively amplify some of the input signal (which can be called the source, or the excitation) and produce a very large output signal at certain frequencies.

What is the source in each of these cases?

1. a guitar string making a musical note
2. a piano string making a musical note
3. the Millennium Bridge swaying
4. the Tacoma Narrows Bridge oscillating with a twisting motion

[Simon]

You have two separate problems there.

The first is probably just the keyboard mapping for the VM. Try typing @ on your keyboard and you will probably get ” (for me this is shift plus the 2 key).

The other sounds like a common audio problem and the solution is here.

[Simon]

You are right: most research papers have rather vacuous introductions such as “The popularity of speech synthesis has been rising in recent years.” or other waffle. Do not do that in coursework – there are no marks for this!

So, how to do better? Don’t simply omit the Introduction. Use it to say something meaningful about what is coming up in your report. Have you got a particular approach to the assignment? Did you find an original angle? What are your concrete goals (and don’t just restate the instructions, but give your interpretation). Are there questions you want answers to?

Use an introduction to set up some expectations in the mind of the reader, then make absolutely sure to deliver them later in the paper. Pose questions in the Introduction but don’t give answers. Motivate the reader to want to read on, to find out the answer. Use the Conclusion to remind the reader what was promised and how you have delivered it, leaving them feeling satisfied.

See also this post.

[Author]

Posts