Virtual Box, Ubuntu, HTK

Demi efisiensi waktu, hari ini terpaksa nginstal2 di kompie orang. Sekalian we dicatet..

1. Download Ubuntu (12, i-386) dan Virtual Box
2. Install Virtual Box, klik sini

• ganti bahasa ke bahasa Inggris (sebelumnya bahasa Jepang)
• File, Preferences, Language, klik sini, dan klik sini

3. Install Ubuntu
4. Install HTK, klik di sini dengan berbagai modifikasi

• download HTK dan cari tempat instalasi yang diinginkan

 extract, tar -xvzf namafile.trgz
./configure

• ubah lokasi default  binaries, yang tadinya “/usr/local/bin”
• masuk ke skrip configure, edit prefix jadi misalnya /home/namaorang/bin/htk-3.4.1/

make all

• error: X11/Xlib.h: No such file or directory
• solusi: sudo apt-get install libx11-dev

make install

• errors, e.g.: cannot create regular file ‘/usr/local/bin/HSLab’: Permission denied
• solusi: ubah script configure (lokasi binaries, prefix, dari yang tadinya /usr/local/bin/ jadi misalnya /home/namaorang/bin/htk-3.4.1/)
• ulangi langkah dari ./configure

5. Display shortcut in file browser (in Ubuntu 12)

• tekan Ctrl+L : view full path
• tekan Ctrl+2: view as list (bukan icon)

6. Edit path (masukkan lokasi binaries sebagai path), cek apakah HTK bisa berjalan normal

• cek path

echo $PATH

• edit path

PATH=$PATH:/home/newpath

• cek apakah HTK bisa berjalan

HVite -V

• jika tidak terdapat error, berarti sudah OK!

7. Sharing folder antara Ubuntu (Guest OS) dan Host OS, klik sini, atau klik sini

• install Guest Addition
• dari jendela virtual box (ketika Guest OS sedang berjalan), klik Devices/Insert Guest Additions CD Image…
• tunggu, lalu ketika diminta, tekan enter
• hasil: /media/VBOXADDITIONS_4.3.6_91406 sudah di-mount

cd /media/VBOXADDITIONS_4.3.6_91406/
./autorun.sh

• ketika selesai, reboot atau restart Virtual Box (Guest OS)
• klik pada jendela Virtual Box (Guest OS): Devices, Shared Folder settings…
• setting folder dengan cara menekan tombol plus, lalu masukkan folder pada Host OS yang diinginkan sebagai shared folder, misal ubuntu
• setting shared folder pada ubuntu
• buat folder yang diinginkan, misal /media/ubuntuVB
• hubungkan dengan shared folder pada Host OS dengan perintah

sudo mount -t vboxsf ubuntu /media/ubuntuVB

8. Selamat bereksplorasi, klik di sini

Speech recognition with hidden markov model (HMM)

Recommended link/lecture (extremely well-written)
1. ASR with HMM
John-Paul Hosom, CSLU, Oregon Health & Science Univ, click here

2. Statistical Data Mining tutorials:
– Clustering with Gaussian Mixtures
– Probability Densities in Data Mining
– Learning Gaussian Bayes Classifiers
– Learning with Maximum Likelihood
– others
Andrew W. Moore, CS, CMU, click here

Protected: Flow HInit

This content is password protected. To view it please enter your password below:

Password:

Kumpulan Error di HTK

Udah telat banget sih, tapi mencoba mencatat error yang ditemui selama troubleshooting.
Sekalian nyoba bikin tabel, tehe 😀

Kumpulan Error di HTK

Error	Penjelasan	Analisis
+7321	CreateInsts: Unknown label q	Phoneme q yang ditemui pada data tidak ditemui pada list phoneme
+5021	GetChkedInt: Integer Arg Required for m option	Saat passing argumen ke HInit, opsi -m tidak diikuti integer apapun
+2121	HInit: Too Few Observation Sequences [2]	Jumlah observation sequences (jumlah utterance) kurang. Ketika dicek, minimum utterance adalah 3

The fundamentals of HTK

Recognizer = to effect a mapping between sequences of speech vectors and the wanted underlying symbol sequences.

Two problems make this very difficult.
Firstly, the mapping from symbols to speech is not one-to-one since different underlying symbols can give rise to similarspeech sounds. Furthermore, there are large variations in the realised speech waveform due tospeaker variability, mood, environment, etc.
Secondly, the boundaries between symbols cannot be identified explicitly from the speech waveform. Hence, it is not possible to treat the speechwaveform as a sequence of concatenated static patterns.

Isolated word recognition

Objective: To overcome problem of not knowing the word boundary locations

Means: the speech waveform corresponds to a single underlying symbol (e.g. word) chosen from a fixed vocabulary.
Limitation: this simpler problem is somewhat artificial, real life: continuous speech case.

The isolated word recognition problem can thenbe regarded as that of computing

arg max{P(wi|O)}
i

How to compute probability: Bayes Rule:
P(wi|O) = (P(O|wi)P(wi))   /P(O)

prior probabilities P(wi),