{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

akunkle_5526_hw1

akunkle_5526_hw1 - Arthur Kunkle ECE 5526 HW#1 1 The...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Arthur Kunkle ECE 5526 HW #1 1. The following two speech spectrograms were taken from ECE 5526 slides: CH1 – Acoustic Theory and Speech Production.ppt. TIMITDICT.TXT was used to map the words to the phonetic decompositions. The colored sets of phonemic symbols have corresponding colored regions in the spectrograms to illustrate the identified regions. Phonemes: /t uw1/ /p l ah2 s/ /s eh1 v ax n/ /ih1 z/ /l eh1 s / /dh ae1 n/ /t eh1 n/
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Phonemes: /dh ax / /sh ih1 p/ /w ax z / /t ao1 r n/ /ax p aa1 r t/ /ao1 n/ /dh ax / /shaa1 r p / 2. A new file: phenome_categories.txt (included) was created that has the following format: <phoneme>:<category_name> The appropriate categories were obtained by using slide #3 from the Chapter 2 presentation. The specgram_nist Matlab script was updated to specgram_nist_q2.m (included). The category file lookup is done and the category is printed next to the phonemic symbol on the spectrogram. Please note, not all phonemes were included in the language tree in the presentation. If a phoneme is not able to be categorized, “(???)” is printed instead. Below are Matlab outputs from the script:
Background image of page 2
FSJK1/sa1 FSJK1/sa2
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
3.
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}