1. CMUSphinx and pocketSphinx

2. Windows install Make subdirectory CMUSphinx
Mine is d:\Stephans\CMUSphinx
From download snapshot of pocketsphinx, sphinxbase, and sphinxtrain to your CMUSphinx directory
I have made window binaries. They are available from the class web page.
If you get binaries, you still need to get the full sphinxtrain file as well (so you will need to download two versions of sphinxtrain)
First get and decompress complete version
Second, get executables. Put executables in SphinxTrain\bin\Release (you will need to make this dirtectory)
This way the directory+file structure is the same as if you had compiled the files
Put binaries of sphinxbase in CMUSphinx/sphinxbase/bin/Release
Put binaries of pocketsphinx in CMUSphinx/pocketsphinx/bin/Release
To run on android, you need to get the full version of pocketsphinx. But this only compiles on linux. We will do this later
The non windows binaries requires MS Visual Studio 2010 (I used Visual Studio 2010 Ultimate)
If you are a student, you can get it for free from
Or find MSDNAA link at
You will also need an eecis account. You can sign up for one.
The snapshots include .sh visual studio 2010 project files (earlier versions will not work)
Open visual studio. File->open->Preoject/Solution. Navigate to and select .sl file. To build: Build->Build solution
First download and build sphinxbase
Before buildigng, switch to release.
Select Build -> Configuratrion Manager: under “Active solutions configuration:” Change from Debug to Release
Then pocketsphinx and sphinxtrain
You need perl and python
For perl, get activestate’s activeperl:
For python get v2.7.X
Once python is installed, add the directory to you path
Add path to sphinxtrain binaries
If downloaded binaries, then add path to where

3. Running pocketsphnix
Note audio file in CMUSphinx\pocketsphinx\test\data\goforward.raw
Open terminal and
Change directory to d:\Stephans\CMUSphinx\pocketsphinx\bin\Release
Pocketsphinx_batch.exe should be there, unless compile failed
Make file ctlFile.txt with text of the name of the file we will decode
goforward
Make file called argFile.txt with contents (more about these later)
-hmm ../../model/hmm/en_US/hub4wsj_sc_8k
-lm ../../model/lm/en/turtle.DMP
-dict ../../model/lm/en/turtle.dic
Move
CMUSphinx/sphinxbase/bin/Release/sphinxbase.dll To
CMUSphinx/pocketsphinx/bin/Release
CMUSphinx\pocketsphinx\test\data\goforward.raw
CMUSphinx\pocketsphinx\bin\Release\goforward.raw
run
pocketsphinx_batch.exe -argfile argFile.txt -cepdir ../../test/data -ctl ctlFile.txt -cepext .raw -adcin true -hyp out.txt
Note: the command line arguments must be in this order!!
Where
-argfile argFile.txt defines the name of the arguments file. These aurgments are displayed on the screen when the program runs. You can check if they match
-cepdir ../../test/data defines the path to the files to be processed
-cepdir must come before -ctl
-ctl ctlFile.txt defines the ctlFile, which contains the name of the files to process. These names cannoy have the path or the extension
-cepext .raw defines the extension of the files in the ctlFile
-adcin true means that the files are audio files
-hyp out.txt defines the output file
More details on the parameters are
After running, the outfile contains
go forward ten meters (goforward )

4. Make and decode a new audio file
Open windows sound recorder
Record “go forward ten meters”
Save as myGoForward.wma
Saves as .wma file
Get wma to wav converted
Save as c:\pocketsphnix\test\data\myGoForward.wav
I use 4musics multiformat converted. Other converters should work
Change ctlFile.txt to
myGoForward
In terminal run
pocketsphinx_batch.exe -argfile argFile.txt -ctl ctlFile.txt -cepdir ./ -cepext .wav -adcin true -hyp out2.txt
Check that out2.txt says go forward ten meters

5. Make your own acoustic model and language
We will go over the what is going on later. But first, let’s try the process.
Alternatively, you can read the about what is going on first and then return to this section
Download data
Get mswav version
Save it to your CMUSphinx directory
Decompress

6. models Three types of models are used acoustic model
Used to model the sound of a phone
Typically, this a HMM is used
Each phone has a HMM
Mapping from HMMs to phones
Since the acoustic model is a HMM, in the CMU Sphinx the HMM is the same as the acoustic model
phonetic dictionary
Maps phones to words
In CMU Sphinx, .dic files are dictionary files
language model
Used to determine sequences of words are allowed. For example, “he super run the sally” is not allowed in the language model

7. Set up config file From CMUSphinx\SphinxTrain\etc
Copy
feat.params
sphinx_train.cfg
To CMUSphinx\an4\etc
Sphinc_train.cfg is the main configuration file
Open sphinx_train.cfg in an editor
Line 6: $CFG_DB_NAME = “an4”;
Line 7: $CFG_BASE_DIR = "d:\\stephans\\CMUSphinx\\an4";
Line 8: $CFG_SPHINXTRAIN_DIR = "d:\\Stephans\\CMUSphinx\\SphinxTrain";
Line 11: $CFG_BIN_DIR = "d:\\Stephans\\CMUSphinx\\sphinxbase\\bin\\Release";
Line 13: $CFG_SCRIPT_DIR = "d:\\Stephans\\CMUSphinx\\SphinxTrain\\scripts";
Check out line These say where the wav files are and that we are using mswav, which is what we downloaded
Line 232: $DEC_CFG_DB_NAME = 'an4';
Line 233: $DEC_CFG_BASE_DIR = 'd:\\Stephans\\CMUSphinx\\an4';
Line 234 does not seem to matter
Line 239: $DEC_CFG_BIN_DIR = "d:\\Stephans\\CMUSphinx\\pocketsphinx\\bin\\Release";
Save sphinx_train.cfg

8. Other changes copy sphinxbase.dll from
CMUSphinx\sphinxbase\bin\Release To
CMUSphinx\SphinxTrain\bin\Release
In CMUSphinx\an4\etc directory, copy or rename
an4.ug.lm.DMP to an4.lm.DMP
Open CMUSphinx\SphinxTrain\scripts\sphinxtrain.in in an editor
Line 3: sphinxpath="d:\\Stephans\\CMUSphinx“
In many places is /lib/sphinxtrain. Change this to /SphinxTrain
Copy files
From CMUSphinx\pocketsphinx\bin\Release, copy
pocketspinx_batch.exe and pocketsphinx.dll to CMUSphinx\SphinxTrain/bin/Release
Try skipping this and setting line 243 of .cfg

9. check Open a cmd prompt Type path and make sure that the directory to
python is there
SphinxTrain\bin\Release is there

10. Run training Change to CMUSphinx\an4 directory Run
python ..\SphinxTrain\scripts\sphinxtrain.in run
This will take a while (15 minutes)
Results from test is sentence error rate of 45% (nearly half of the sentences had at least one error) and 15.7% word error rate (15.7% of the words were incorrectly estimated)
This can fail because python was not installed or the path to python was not set
Or the path to SphinxTrain

11. Check log Open an4.html Check for errors
MODULE: 30 Training Context Dependent models
A few errors of type: “Failed to align audio to trancript: final state of the search is not reached” are acceptable
MODULE: 50 Training Context dependent models
At the very end is the test decoding
Open log file
Note parameters for running decoding, specifically, where Hmm, dic, and lm is

12. Test with your own voice sample
Record sample
Convert to .wav
Run pocketsphinx_batch
pocketsphinx_batch
-hmm d:\Stephans\CMUSphinx\an4/model_parameters/an4.cd_cont_200
-lw 10 -feat 1s_c_d_dd
-beam 1e-80 -wbeam 1e-40
-dict d:\Stephans\CMUSphinx\an4/etc/an4.dic
-lm d:\Stephans\CMUSphinx\an4/etc/an4.lm.DMP
-wip 0.2 -ctl d:\Stephans\CMUSphinx\an4/myTest/ctlFile.txt
-ctloffset 0
-ctlcount 130
-cepdir d:\Stephans\CMUSphinx\an4/myTest -cepext .wav
-hyp d:\Stephans\CMUSphinx\an4/myTest/results.txt
-agc none
-varnorm no
-cmn current
-adcin true

13. test

14. background
At a first approximation, words are a sequences of sounds, where each sound is a phone.
However, the exactly pronunciation of a phone depends on the phones before and after.
Diphones are two phones. Diphones are less impacted by the phones that come before or after.
Triphones and quinphones are possible. The general name is senone
While there are many phones, not all combinations of a phone is a word. Thus, we should not simple recognize phones, by recognize words as a sequence of phones
Besides phones are fillers (e.g., breath, “um”). An Utterance is a sequence of words and fillers
Utterances are separated by a pause

15. models Three types of models are used acoustic model
Used to model the sound of a phone
Typically, this a HMM is used
Each phone has a HMM
Mapping from HMMs to phones
Since the acoustic model is a HMM, in the CMU Sphinx the HMM is the same as the acoustic model
phonetic dictionary
Maps phones to words
In CMU Sphinx, .dic files are dictionary files
language model
Used to determine sequences of words are allowed. For example, “he super run the sally” is not allowed in the language model

16. Running with other models
Many acoustic and language models are available at

17. Building Your Own Acoustic Model and Language Model
Building your own models is time consuming
Acoustic models require
Lots of recordings of people saying words and sentences
Not that difficult to do
Accurate transcription of the recording
Time consuming
There are many acoustic models available online
It is possible to take an existing model are quickly adapt it to a particular speaker
Language Model
Different systems need different language models
A voice control for your TV needs to recognize only a few words like “volume up,” “change channel,” …
A voice driven composer needs to recognize a different set of words
The performance of the recognizer is improved if your language only considers the relevant words.
You can take an existing language model and trim it to what you need, or make on from scratch
Many models are available from

18. example To explore acoustic and language models, get the AN4 database
Save it to your CMUSphinx directory
Decompress
Also, explore the PDA dataset
This data is from letters and numbers, e.g., “A”, “B”, “19”
We can test this system by saying things like “A”, “B”, etc.

19. Acoustic model
The acoustic model is used to translate recorded sounds into labeled phones,
e.g., recorded sound in file asc.wav is “AH”
Roughly speaking, acoustic models take the sound sample as input and the quality of fit as output
asc.wav -> AH-Model-> -12
asc.wav -> AY-Model-> -14 …
AH-Model gives a better fit of the recorder sound
Making a acoustic model is called training
Inputs to training are audio files and transcriptions
Challenge: Usually the audio file has many phones, not just one
E.g., from AN4 data set, an audio file contains a recording of the words “TWO SIX EIGHT FOUR FOUR ONE EIGHT “
CMUSphinx\an4\wav\an4_clstk\fash\cen7-fash-b.wav
E.g. from PDA data set, an audio file might contain a recording of the words: “MARGINS HISTORICALLY HAVE PEAKED BY MID YEAR HE SAYS”
CMUSphinx\PDA\PDAs\001\PDAs01_001_1.wav

20. Transcriptions
Approach one: the recording from the PDA set is transcribed as: M AA R JH AX N Z SIL HH IX S T AO R IX K AX L IY SIL ...
Two problems with approach one
If the word margins are in other files, we need to enter the pronounciation of the word twice
There are two ways that people pronounce historically
HH IX S T AO R IX K AX L IY
HH IX S T AO R IX K L IY (this one actually says historicly, which is incorrect)
Two stage transciptions (results in many files)
Transcription file: gives the words spoken
This file contains one line for each file used in training
The line contains the text of the words spoken and the filename (without extension such as .wav)
The AN4 dataset includes the file an4_train_transcription and it includes the line: <s> TWO SIX EIGHT FOUR FOUR ONE EIGHT </s> (cen7-fash-b)
The PDA dataset includes the file PDAs.train_all.sent and it includes the line: MARGINS HISTORICALLY HAVE PEAKED BY MID YEAR HE SAYS (PDAs01_041)
Hmm, this is missing the <s> and </s>, I think that the software requires <s> and </s>.. To use the pda data set, add <s> and </s>
Dictionary file
A mapping from words to phones (elementary spoken sounds)
Allows words to have multiple pronunciations
E.g., the AN4 dataset includes the file an4.dic and it includes the lines
ELEVEN IH L EH V AH N
ELEVEN(2) IY L EH V AH N
E IY
By combining the transcript file and dictionary file, the sounds in each recorded audio file can be determined
However, it is a bit tricky to determine which part of the audio file corresponds to which sound.
This is a major challenge facing training
Recall, the overall goal of training is to find models for each sound. But to make the training process easier for the users, we only provide recordings of words and sentences.

21. Training
Files needed
your_db_train.fileids - List of files used for training
E.g., AN4 includes an4_train.fileids
Format
path/filename (without extension!)
The path is from where the SphinxTrain program is executed
E.g., an4_train.fileids path is relative to where AN4 /etc directory. So SphinxTrain needs to be run from this directory
your_db_train.transcription - Transcription for training (described on previous slide)
your_db.dic - Phonetic dictionary (described on previous slide)
your_db.filler - List of fillers and what they map to
Fillers are things like silence, breathing, “um” etc.
Fillers should also be used in the transcript
E.g., <s> TWO +UM+ SIX EIGHT FOUR FOUR ONE EIGHT </s>
Fillers use the + sign before and after
During training, models for fillers will be computed
Decoding is more complicated
Fillers are allowed to be added, but there is some penalty
the fillers are ignored when computing the probability of a sequence of words
E.g., the language model might tell us that “go to bed” is common, and “go up bed” is uncommon. If the decoder detect “go um to bed” it translates it to “go to bed”
For some reason, fillers are not used in the an4 and PDA transcript files
<s>, </s>, SIL are silence are included
SMACK is listed in the PDA filler file, but not in the transcript
File format
</s> SIL
<s> SIL
<sil> SIL
++INHALE++ +INHALE+
your_db.phone - Phoneset file
a list of all labels of phones used (sounds), including fillers
E.g., an4.phone: AA, AE, AH, …
Every phone label used in the dictionary must be in the .phone file AND the filler labels

22. Must have sphinxtrain/bin/debug in path
Must copy sphinxbase.dll to sphinxtrain/bin/debug or set path to
Move pocketsphinix exe and dll
Edit sphinxtrain.in to remove /log and set prefix to path
Must use python 2.7
Delete an4.html before running
This is a log file. Will not exist before the first run. But if you run and find errors, you can check it. But make sure to delete it before running so you can see the errors
Change an4.ug.lm.DMP to an4.lm.DMP

23. Language model
Language models define which combinations of words are allowed.
And, which combinations are more common or less common
Language model defines
How often a word appears
Words: Go, stop, hi, bye
How often combinations of word appear
Combinations with 2 words: Go forward; go back; …
Note that the length of these sequences can be 2, 3, ..
The language cannot specify all combinations of any length. So only combinations up to some length (e.g., 2 or 3) are specified
.ARPA files specify the language with a particular format
See for some details
See next slide
There is an online language maker that takes sentences, counts the combinations of words and makes a ARPA file
If you make your own arpa file,
you must sort it before using
sphinx_lm_sort < unsorted.arpa > sorted.arpa
Then convert to lm
sphinx_lm_convert –I sorted.arpa –o sorted.lm.DMP
Note that sometimes files that end in .lm are in the arpa format
The DMP can be used to decode

24. ARPA format <header - information ignored by applications>
\data\
ngram 1=9
ngram 2=11
ngram 3=3
\1-grams:
<unk>       
</s>
<s>  
When
will
the  
Stock
Go   
Up   
\2-grams:
<s> When    
<s> the     
<s> Up      
When will   
will </s>   
will the    
the </s>    
the Go      
Stock Go    
Go Up       
Up </s>     
\3-grams:
<s> When will     
When will the     
Go Up </s>  
\end\
/data/ specifies how many entries
The numbers are log10 of probabilities
For the 3-gram entry
-1.2 go to bed -.1.
The first number, -0.2 is log10 of the probability that the last word (bed) occurs given the first two words have occurred
There might be other 3-grams like go to sleep, etc.
The second number is the probability that no words occur after this 3-gram
For the 2-gram entry
-.2 go to -10.1
The first number is the log10 of the probability that to occurs after go
The second number is the probability that no words will come after go to
Not so likely
For the 1-gram
go -0.27
The first number is the probability that go occurs
Go can occur by itself
The second number is not the log10 of a probability, but is log10 of a weight (it could be log10 of a probability, but does not have to be)

25. Running pocketsphinx on android
I could only get this working on Linux.
Windows might be possible (I didn’t try MAC)
The instructions here are almost correct
Follow instructions for getting and compiling sphinxbase and pocketsphinx
Get PocketSphinxDemo.tar.gz
Import that to eclipse
File->import->Existing Projects into workspace-(next)-
Select “Select archive file”
browse and select PocketSphinxDemo.tar.gz
In an editor, open eclipse/workspace/PocketSphinxDemo/jni/Anroid.mk
In the second to last line
Change
LOCAL_STATIC_LIBRARIES := sphinxutil sphinxfe sphinxfeat sphinxlm pocketsphinx To
LOCAL_STATIC_LIBRARIES := pocketsphinx sphinxlm sphinxfeat sphinxfe sphinxutil
(back to instructions from web page)
Build,
Change directory to eclipse/workspace/PocketSphinxDemo/jni
Android/andtroid-ndk-r7b/ndk-build –B
Adjust properties->Builders as described on web page
I’m not sure how important this is.
Swig makes an interface between java and c++, but these files have already been down loaded.
ndk is run from the command line

26. On phone
(the directory should be /mnt/sdcard/Android/data/edu.cmu.pocketsphinx)
adb shell
mkdir /mnt/sdcard/Android/data/edu.cmu.pocketsphinx
cd /mnt/sdcard/Android/data/edu.cmu.pocketsphinx
Make directory struction as shown on web page
/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/hmm
/mnt/sdcard/Android/data/edu.cmu.pocketsphinx /hmm/en_US
/mnt/sdcard/Android/data/edu.cmu.pocketsphinx /hmm/hub4wsj_sc_8k
Not sure if this is needed.
/mnt/sdcard/Android/data/edu.cmu.pocketsphinx /lm
/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/lm/en_US
Cd to CMUSphinx/pocketsphinx/model/hmm/en_US/
Android/android-sdk/platform-tools/adb push ./hub4wsj_sc_8k /mnt/sdcard/Android/data/edu.cmu.pocketsphinx/hmm/en_US/hub4wsj_sc_8k
Cd to CMUSphinx/pocketsphinx/model/lm
Android/android-sdk/platform-tools/adb push ./en_US /mnt/sdcard/Android/data/edu.cmu.pocketsphinx/lm/en_US/

27. In eclipse
In RecognizerTask.java, change code to include the correct path
This path must match the path where the model files are located
pocketsphinx.setLogfile("/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/pocketsphinx.log"); Config c = new Config(); /* * In 2.2 and above we can use getExternalFilesDir() or whatever it's called */ c.setString("-hmm", "/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/hmm/en_US/hub4wsj_sc_8k"); c.setString("-dict", "/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/lm/en_US/hub dic"); c.setString("-lm", "/mnt/sdcard/Android/data/edu.cmu.pocketsphinx/lm/en_US/hub DMP"); c.setString("-rawlogdir", "/mnt/sdcard/Android/data/edu.cmu.pocketsphinx"); // Only use it to store the audio
Note that these lines are also changed if you use different models
Build, run and test

28. Windows install Requires Android NDK
Flex for windows:
Bison for windows:
Get CMUSphinix from here: ??
Note that this contains the

29. Follow directions from
Or google: pocketSphinx android
Or:
But order of libs at the end need to be reversed
Only compiles on linux, because is need yacc

30. resources:

31. Voice activity detection
VAD is used to detect if anyone is speaking