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)}

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

prior probabilities P(wi),


Browser ke browser

Personal assessment

Internet Explorer:
+ Basic, ada di semua windows

Mozilla Firefox:
+ Beragam pilihan plug-in
+ Ada suggestion ttg harmful site
– Terakhir kali mencoba (2007?) berat di memory

+ Ringan (ketimbang Firefox, teruji -2007)
+ Speed Dial (waktu jaman itu sih keren banget)
+ Bisa dengan mudah membuka accidentally closed tab
– Banyak kurang menyupport fitur2 di website (lupa jenis fiturnya apa)
– Tidak ada suggestion ttg harmful site

+ Opsi translate
+ integrated url box & search box
+  Ada suggestion ttg harmful site