Re: [asterisk-users] Voicemail to text for Asterisk
On 22/10/2012 at 16:02 -0400, Bryant Zimmerman wrote: > Carlos > > I have tried several solutions and non of them have been worth the > money. I have worked with transcription companies and they are the > best but they are expensive. If you do find something that works let > the groups know as there are a few of us out here that are looking for > that holy grail of speech to text. There is no holy grail yet, speech technology deployment requires a close cooperation between the speech technology provider and the users. It's not plug and play but after some joint efforts automated transcriptions must be useful. If anyone wants to experiment with CMUSphinx-based automated solution to transcribe voicemails, drop me a note. The results could be pretty interesting. signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Open source speech recognition engine?
On 21/04/2012 at 16:41 +0300, Carl-Fredrik Enell wrote: > Dear all, > > I am looking for an open source speech recognition engine for a hobby > project. > > There used to be a Sphinx interface for the generic speech API > (http://scribblej.com/svn/) but it does not compile on Asterisk > versions later than 1.6.x > > Could anybody direct me on how to update this code, or should I simply > change to the AGI script approach? To use asterisk with the open source CMUSphinx speech recognitoin engine please try AST-UniMRCP and unimrcp server with the pocketsphinx plugin: http://code.google.com/p/unimrcp/wiki/PocketSphinxPlugin It's a recommended way to use Pocketsphinx with asterisk. It's somewhat hard to compile but it will work fine if you will do everything properly. signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Asterisk- speech to text(Voicemail totext message)
В Чтв, 23/09/2010 в 14:21 -0500, Danny Nicholas пишет: > >FWIW, the current state of Speech-to-text will let you do a 70-95% accurate > translation of > >incoming voicemails depending on clarity/dialect/training. Also depends on > language of > >"native" speakers. For 100% reliability, this still requires Human > intervention. > > I'd like to do this too. Poking around, it looks like res_speech.so is the > library to enable it, but an actual separate program to convert from voice > to text is needed, like Sphinx or VXI? I haven't found anything yet that > describes how to connect it to voicemail. Examples are welcome, if anyone > has one to point at/paste. > > Looking at Sphinx and the available documentation, I think these things to > be true. > #1 - res_speech.so isn't necessary since Sphinx operates as a external > module as opposed to the resident modules of Vestec and Lumenvox. > #2 - Didn't really find a good "on-the-fly" example of processing the file > as it came in. Hello guys I've created a little HOWTO about voicemail transcription with Asterisk and pocketsphinx here: http://nsh.nexiwave.com/2010/09/voicemail-transcription-with.html try it. If you have any other questions just ask --- Nexiwave - Speech Mining For Call Centers http://nexiwave.com signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Speech To Text on linux with asterisk
В Чтв, 16/09/2010 в 12:44 +0530, DHAVAL INDRODIYA пишет: > Thanks for update if a file is converted to text then where can i find > a text file like after running > pocketsphinx_continuous command where text saved. Text is in the last line: 0: we've entered the property the identification number of a conflict signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Speech To Text on linux with asterisk
В Чтв, 16/09/2010 в 10:35 +0530, DHAVAL INDRODIYA пишет: > > Hi Nickolay, > > here i attached my file. please have a look into it. Hello DHAVAL As I wrote your file has wrong format. $ file ask-propertyid.WAV ask-propertyid.WAV: RIFF (little-endian) data, WAVE audio, GSM 6.10, mono 8000 Hz See GSM 6.10 there. You need to convert it to PCM sox ask-propertyid.WAV -e signed-integer ask-propertyid-converted.WAV Then decode. signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Speech To Text on linux with asterisk
2010/9/15, DHAVAL INDRODIYA : > Hello i have tried to convert through sphinx as suggested by Nickolay > > i am not getting convert my simple audio file. > > i am having following error while i fire following command > > pocketsphinx_continuous -infile /usr/etc/ask-propertyid.WAV -samprate 8000 \ > -hmm /usr/etcSpeechToText/Communicator_semi_40.cd_semi_6000 -lm > lm_giga_20k_nvp_3gram.lm.DMP > > *FATAL_ERROR: "continuous.c", line 149: Failed to calibrate voice activity > detection* Hi That's a progress already. I suspect this file has wrong format. It must be little-endian 16-bit PCM with sample rate 8kHz. uLaw will not work. It's also nice to have a little period of silence in the beginning of the file. Can you provide the file itself/share it somehow so I could take a look. -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Speech To Text on linux with asterisk
В Втр, 14/09/2010 в 14:00 +0530, DHAVAL INDRODIYA пишет: > Thanks for update. > > is there any command for using sphinix to convert speech to text Yes, first of all make sure you compiled latest snapshot. Then run # sphinx_lm_sort < lm_giga_20k_nvp_3gram.arpa > lm_giga_20k_nvp_3gram.arpa.sorted # sphinx_lm_convert -i lm_giga_20k_nvp_3gram.arpa.sorted -o lm_giga_20k_nvp_3gram.lm.DMP This will create a language model lm_giga_20k_nvp_3gram.lm.DMP And finally convert audio pocketsphinx_continuous -infile your_audio_file.wav -samprate 8000 \ -hmm Communicator_semi_40.cd_semi_6000 -lm lm_giga_20k_nvp_3gram.lm.DMP -- Nexiwave - Speech Mining Solution For Call Centers http://nexiwave.com signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Speech To Text on linux with asterisk
В Втр, 14/09/2010 в 01:55 -0400, Zeeshan Zakaria пишет: > It is simply not possible, though it might be in the distant future. Let me respectively disagree with you. It's perfectly possible even with open source tools. You can download pocketsphinx from http://cmusphinx.sourceforge.net To convert speech to text you need to download Communicator acoustic telephone model and LM giga large vocabulary language model. http://www.speech.cs.cmu.edu/sphinx/models/communicator_mar2008/communicator_semi_6000_20080321.tar.gz http://www.keithv.com/software/giga/ -- Nexiwave - Speech Mining Solution For Call Centers http://nexiwave.com signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Opensource Speech recognition for Asterisk
Hello Vieri
Indeed, acoustic model is missing. However, if you are really
interested, we can provide you Spanish model for telephone speech in a
week or so. If you can provide some test database with recordings, it
will be even better.
Contact me for details.
--
Nexiwave - Speech Indexing Solution For Call Centers
http://nexiwave.com
2010/8/24, Vieri :
> Hi,
>
> Sorry to drop in on this thread but I'm relatively new to Sphinx and speech
> recognition. I'd like to know if anyone has successfully setup speech
> recognition in Asterisk for Spanish users. Sphinx doesn't seem to have
> Spanish acoustic and language models and I don't think I'll ever have the
> time or know-how to make my own.
> My requirements are similar to the OP's:
> basic "yes", "no", get an 8 digit number, etc.
>
> Actually, "yes" ("si") and "no" work well with the English models. However,
> accuracy is not that great when it comes to recognizing digits zero to nine
> in Spanish.
>
> Thanks for any suggestions,
>
> Vieri
>
> --- On Tue, 8/24/10, Bob Kleiner wrote:
>
>> From: Bob Kleiner
>> Subject: Re: [asterisk-users] Opensource Speech recognition for Asterisk
>> To: asterisk-users@lists.digium.com
>> Date: Tuesday, August 24, 2010, 7:30 AM
>> > Thanks guys. A lot of info here
>> :-)
>> >
>> > I am wondering if anyone followed this and it was
>> working for them:
>> >
>> > http://scribblej.com/svn/
>> >
>> > ???
>>
>> Hello Bruce
>>
>> We successfully deployed it and now saving thousands on
>> commercial ASR
>> ports. It seems users are rather happy with it. The
>> recognition seems
>> pretty accurate. Of course it has it's own limitations but
>> so any
>> other technology. It will not hurt if some of your users
>> will benefit
>> from ASR.
>>
>> > I am not looking for anything fancy. The basic "yes",
>> "no", dialing a
>> > number, asking for agent, etc...out of which probably
>> the hardest is a 10
>> > digit number to be asked to be dialed.
>>
>> Yes, that should work. It also supports JSGF grammars, so
>> you should
>> be able to recognize digit strings easily.
>>
>> And if you want something serious, there are at least two
>> open source products
>> providing ASR over standard MRCP protocol. They also use
>> CMUSphinx, so
>> provide the same accuracy
>>
>> Zanzibar http://www.spokentech.org/writing-speechlets.html
>> Cairo http://www.speechforge.org/
>>
>> Though Cairo is a bit dated.
>>
>> --
>> _
>> -- Bandwidth and Colocation Provided by http://www.api-digital.com --
>> New to Asterisk? Join us for a live introductory webinar
>> every Thurs:
>>
>> http://www.asterisk.org/hello
>>
>> asterisk-users mailing list
>> To UNSUBSCRIBE or update options visit:
>> http://lists.digium.com/mailman/listinfo/asterisk-users
>>
>
>
>
>
> --
> _
> -- Bandwidth and Colocation Provided by http://www.api-digital.com --
> New to Asterisk? Join us for a live introductory webinar every Thurs:
>http://www.asterisk.org/hello
>
> asterisk-users mailing list
> To UNSUBSCRIBE or update options visit:
>http://lists.digium.com/mailman/listinfo/asterisk-users
>
--
_
-- Bandwidth and Colocation Provided by http://www.api-digital.com --
New to Asterisk? Join us for a live introductory webinar every Thurs:
http://www.asterisk.org/hello
asterisk-users mailing list
To UNSUBSCRIBE or update options visit:
http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Opensource Speech recognition for Asterisk
> Hi Everyone, > > Has anyone got any opensource speech recognition software to work with > Asterisk? Please only list WORKING ones. Not the "theoretically" should work > ones! Hi I definitely suggest you to try CMU Sphinx connector for Asterisk. You can find all required information here http://scribblej.com/svn/ If you need any help with setup, just ask. -- Nexiwave - Speech Indexing Solution For Call Centers http://nexiwave.com signature.asc Description: This is a digitally signed message part -- _ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- New to Asterisk? Join us for a live introductory webinar every Thurs: http://www.asterisk.org/hello asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
