Pocketsphinx with keyphrase on python

[Paulo Ferreira]

Hello,
I am building a simple program to recognize a few words and i need to reject the out of grammar words so i am using a file with keyphrase and a threshold in order to do this.
Here is my code:

import os
from pocketsphinx import LiveSpeech, get_model_path

model_path = get_model_path()

speech = LiveSpeech(
    verbose=False,
    sampling_rate=16000,
    buffer_size=2048,
    no_search=False,
    full_utt=False,
    #lm=False,
    hmm= os.path.join(model_path,'en-us'),
    #lm= '/home/paulo/PycharmProjects/VoiceRecognition/Data/TAR4858/4858.lm',
    dic = '/home/paulo/PycharmProjects/VoiceRecognition/Data/TAR4858/4858.dic',
    kws = '/home/paulo/PycharmProjects/VoiceRecognition/Data/TAR4858/keyphrase.list'
)

for phrase in speech:
    print phrase.probability()
    frase = str(phrase)
    print frase

Dictionary made with LMTool:

BROWSER B R AW Z ER
COMPUTER    K AH M P Y UW T ER
HELLO   HH AH L OW
HELLO(2)    HH EH L OW
MUSIC   M Y UW Z IH K
OFF AO F
ON  AA N
ON(2)   AO N
OPEN    OW P AH N
TURN    T ER N

Keyphrase.list:

OPEN BROWSER /1e+20/
TURN ON MUSIC /1e+20/
TURN OFF MUSIC /1e+20/
TURN OFF COMPUTER /1e+20/
HELLO COMPUTER /1e+20/

But this is not recognizing any word at all, why this is happening?

[Nickolay V. Shmyrev]

Maybe your microphone is muted. You can add verbose=True to constructor and check the log values.

[christian schuch]

Maybe you should lower the Threshold, this did the Trick for me. I'm using /1e+10/ now and it works flawlessly