Pocketsphinx setKeywordThreshold () problem
I am thinking of using the pocketsphinx offline speech recognition for my application, but its documentation is not clear. If anyone can provide answers to the following question, this will really help me.
-
What is the role (usage) of the setKeywordThreshold (1e-5f) method. What is the minimum and maximum value allowed in this method.
-
I want to provide support for different languages ββand find built-in acoustic models for some languages ββat this link http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ . but I can't figure out which model would be better for which language due to the lag in the documentation. Can anyone suggest me the best built-in acoustic models for the following languages ββ-
(and). Australian English (B). American English (C). British English (G). Canadian English (E). European English (E). Indian English (g). Irish English (hour). New Zealand (i). South African English (C). Russian (K). Spanish (L). French (M). Dutch (P). German
-
I just want to recognize numbers from 1 to 200 in each language. What's the best way to do this?
-
I created a digits.gram file to recognize numbers from 1 to 99, but also recognized the background voice. For example, when any background voice of the drilling machine comes up, it will recognize it as one. How can we recognize numbers only when these numbers are spoken?
digits.gram file
#JSGF V1.0;
grammar digits;
<single> = one | two | three | four | five | six | seven | eight | nine ;
<digit> = <single> |
zero |
ten |
eleven |
twelve |
thirteen |
fourteen |
fifteen |
sixteen |
seventeen |
eighteen |
nineteen |
twenty |
thirty |
forty |
fifty |
sixty |
seventy |
eighty |
ninety |
twenty <single> |
thirty <single> |
forty <single> |
fifty <single> |
sixty <single> |
seventy <single> |
eighty <single> |
ninety <single> ;
source to share
No one has answered this question yet
Check out similar questions: