How to use a keyword list on pocketsphinx

Question

I am building a program with python and pocketsphinx in order to control a Drone with my voice. I have this dictionary:

DOWN  D AW N
GO  G OW
LEFT  L EH F T
RIGHT  R AY T
TURN  T ER N
UP  AH P

If i say a word which is in this dictionary everything works fine, but if i say a word which is not in the dictionary pocketsphinx will try to find the closest match from the dictionary. E.g if i say Stop pocketsphinx will display UP, but if this is the case my program should do nothing. I did search in the internet and i found that this problem can be solved by using a Keyword List, but i can't find information about how to use it with python. This is the code i have so far

#!/usr/bin/env python

import os
from pocketsphinx import LiveSpeech, get_model_path

i = 0
j = 0
frase = ''
tab = [['x','o','o'],['o','o','o'],['o','o','o']]

def move():
    global i,j,frase

    if 'DOWN' in frase and i!= 2:
        i=i+1
    if 'UP' in frase and i!= 0:
        i=i-1
    if 'LEFT' in frase and j != 0:
        j = j - 1
    if 'RIGHT' in frase and j != 2:
        j = j + 1

def draw():
    global i,j
    s = 0
    for l in range(3):
        for c in range(3):
            if tab[l][c] == 'x':
                tab[l][c] = 'o'
                s = 1
                break
        if s == 1:
            break
    tab[i][j] = 'x'
    for p in tab:
        print p


model_path = get_model_path()

speech = LiveSpeech(
    verbose=False,
    sampling_rate=16000,
    buffer_size=2048,
    no_search=False,
    full_utt=False,
    hmm= os.path.join(model_path,'en-us'),
    lm=os.path.join(model_path, 'drone.lm.bin'),
    dic=os.path.join(model_path, 'drone.dict'),
)

for p in tab:
    print p

for phrase in speech:
    frase = str(phrase)
    print frase
    move()
    draw()

I am using a matrix with an X just to simulate the drone. I built the dictionary and the language model using lmtool, provinding a Corpus file.