Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?
This would work if you only care that you get very rough phonetic spellings as Don implied. If you think about it humans cannot do any better. I know personally - I have to spell my name all the time. Perhaps your app could ask them to spell their name, which actually has a shot at reliability of not useability. j On Sat, 31 Jan 2009, Kurian Thayil wrote: Hi Alfred, There is a research project by Carnegie Mellon University (CMU) on a very versatile Speech Recognition Software. Its Sphinx http://cmusphinx.sourceforge.net/html/cmusphinx.php . This application is in raw state and the Version 2 of sphinx could be integrated with Asterisk. Festival (Text to Speech application) that is widely used in asterisk is by CMU. Refer http://www.voip-info.org/wiki-Sphinx . I hope this gives a pretty good start. Sphinx needs to be trained with a language model. But since your requirement is just names it should not be complicated. Also have a look at http://www.speech.cs.cmu.edu/Communicator/ . Something I have not looked into much (and I don't know if it has anything to do with Asterisk). I hope this helps. Regards, Kurian Thayil. On Sat, Jan 31, 2009 at 9:22 AM, Alfred Monticello ajmce...@yahoo.comwrote: I wouldn't have a database to compare names to, each one would essentially be unique and unknown. It's sounding like this idea may be not possible...What high end options are available? I read about lumenvox, but I believe that compares to a known list of names (such as a directory, or Yes No, Digits, etc) Hum... -- *From:* Don Kelly d...@donkelly.biz *To:* Asterisk Users Mailing List - Non-Commercial Discussion asterisk-users@lists.digium.com *Sent:* Friday, January 30, 2009 7:41:02 PM *Subject:* Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? There are solutions ranging from free to many thousands of dollars, with effectiveness ranging from nearly worthless to almost pretty good. A lot depends on your application. The most successful application would match an utterance from a known speaker to a known list of a couple dozen names. For example, if I say Alfred Monticello, the application can easily distinguish this from other list entries such as Don Kelly and Robert Smith. The least successful would attempt to convert an utterance from an unknown speaker to text (which is what your inquiry implies). Even if it clearly understands the speaker, the result could easily be Alphret Mahntichelo. --Don Don Kelly PCF Corp People Come First 651 842-1000 888 Don Kell(y) 651 842-1001 fax -- *From:* asterisk-users-boun...@lists.digium.com [mailto: asterisk-users-boun...@lists.digium.com] *On Behalf Of *Alfred Monticello *Sent:* Friday, January 30, 2009 9:25 PM *To:* asterisk-users@lists.digium.com *Subject:* [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? I'm interested in taking a persons spoken recorded name (First, Last) and converting the two spoken words to text. Is there any solutions out there that would make this possible? ___ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- 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 -- asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?
There are solutions ranging from free to many thousands of dollars, with effectiveness ranging from nearly worthless to almost pretty good. A lot depends on your application. The most successful application would match an utterance from a known speaker to a known list of a couple dozen names. For example, if I say Alfred Monticello, the application can easily distinguish this from other list entries such as Don Kelly and Robert Smith. The least successful would attempt to convert an utterance from an unknown speaker to text (which is what your inquiry implies). Even if it clearly understands the speaker, the result could easily be Alphret Mahntichelo. --Don Don Kelly PCF Corp People Come First 651 842-1000 888 Don Kell(y) 651 842-1001 fax _ From: asterisk-users-boun...@lists.digium.com [mailto:asterisk-users-boun...@lists.digium.com] On Behalf Of Alfred Monticello Sent: Friday, January 30, 2009 9:25 PM To: asterisk-users@lists.digium.com Subject: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? I'm interested in taking a persons spoken recorded name (First, Last) and converting the two spoken words to text. Is there any solutions out there that would make this possible? ___ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?
I wouldn't have a database to compare names to, each one would essentially be unique and unknown. It's sounding like this idea may be not possible...What high end options are available? I read about lumenvox, but I believe that compares to a known list of names (such as a directory, or Yes No, Digits, etc) Hum... From: Don Kelly d...@donkelly.biz To: Asterisk Users Mailing List - Non-Commercial Discussion asterisk-users@lists.digium.com Sent: Friday, January 30, 2009 7:41:02 PM Subject: Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? There are solutions ranging from free to many thousands of dollars, with effectiveness ranging from nearly worthless to almost pretty good. A lot depends on your application. The most successful application would match an utterance from a known speaker to a known list of a couple dozen names. For example, if I say “Alfred Monticello,” the application can easily distinguish this from other list entries such as “Don Kelly” and “Robert Smith.” The least successful would attempt to convert an utterance from an unknown speaker to text (which is what your inquiry implies). Even if it clearly “understands” the speaker, the result could easily be “Alphret Mahntichelo.” --Don Don Kelly PCF Corp People Come First 651 842-1000 888 Don Kell(y) 651 842-1001 fax From:asterisk-users-boun...@lists.digium.com [mailto:asterisk-users-boun...@lists.digium.com] On Behalf Of Alfred Monticello Sent: Friday, January 30, 2009 9:25 PM To: asterisk-users@lists.digium.com Subject: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? I'm interested in taking a persons spoken recorded name (First, Last) and converting the two spoken words to text. Is there any solutions out there that would make this possible? ___ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?
Hi Alfred, There is a research project by Carnegie Mellon University (CMU) on a very versatile Speech Recognition Software. Its Sphinx http://cmusphinx.sourceforge.net/html/cmusphinx.php . This application is in raw state and the Version 2 of sphinx could be integrated with Asterisk. Festival (Text to Speech application) that is widely used in asterisk is by CMU. Refer http://www.voip-info.org/wiki-Sphinx . I hope this gives a pretty good start. Sphinx needs to be trained with a language model. But since your requirement is just names it should not be complicated. Also have a look at http://www.speech.cs.cmu.edu/Communicator/ . Something I have not looked into much (and I don't know if it has anything to do with Asterisk). I hope this helps. Regards, Kurian Thayil. On Sat, Jan 31, 2009 at 9:22 AM, Alfred Monticello ajmce...@yahoo.comwrote: I wouldn't have a database to compare names to, each one would essentially be unique and unknown. It's sounding like this idea may be not possible...What high end options are available? I read about lumenvox, but I believe that compares to a known list of names (such as a directory, or Yes No, Digits, etc) Hum... -- *From:* Don Kelly d...@donkelly.biz *To:* Asterisk Users Mailing List - Non-Commercial Discussion asterisk-users@lists.digium.com *Sent:* Friday, January 30, 2009 7:41:02 PM *Subject:* Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? There are solutions ranging from free to many thousands of dollars, with effectiveness ranging from nearly worthless to almost pretty good. A lot depends on your application. The most successful application would match an utterance from a known speaker to a known list of a couple dozen names. For example, if I say Alfred Monticello, the application can easily distinguish this from other list entries such as Don Kelly and Robert Smith. The least successful would attempt to convert an utterance from an unknown speaker to text (which is what your inquiry implies). Even if it clearly understands the speaker, the result could easily be Alphret Mahntichelo. --Don Don Kelly PCF Corp People Come First 651 842-1000 888 Don Kell(y) 651 842-1001 fax -- *From:* asterisk-users-boun...@lists.digium.com [mailto: asterisk-users-boun...@lists.digium.com] *On Behalf Of *Alfred Monticello *Sent:* Friday, January 30, 2009 9:25 PM *To:* asterisk-users@lists.digium.com *Subject:* [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? I'm interested in taking a persons spoken recorded name (First, Last) and converting the two spoken words to text. Is there any solutions out there that would make this possible? ___ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- 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 -- asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software?
Thanks. This has been useful, I've been toying with Sphinx4 but haven't gotten very far with it yet. Took a while to get my environment set up to compile all the java sources.. should have downloaded the binary distro...:-) From: Kurian Thayil kurianmtha...@gmail.com To: Asterisk Users Mailing List - Non-Commercial Discussion asterisk-users@lists.digium.com Sent: Friday, January 30, 2009 8:08:32 PM Subject: Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? Hi Alfred, There is a research project by Carnegie Mellon University (CMU) on a very versatile Speech Recognition Software. Its Sphinx http://cmusphinx.sourceforge.net/html/cmusphinx.php . This application is in raw state and the Version 2 of sphinx could be integrated with Asterisk. Festival (Text to Speech application) that is widely used in asterisk is by CMU. Refer http://www.voip-info.org/wiki-Sphinx . I hope this gives a pretty good start. Sphinx needs to be trained with a language model. But since your requirement is just names it should not be complicated. Also have a look at http://www.speech.cs.cmu.edu/Communicator/ . Something I have not looked into much (and I don't know if it has anything to do with Asterisk). I hope this helps. Regards, Kurian Thayil. On Sat, Jan 31, 2009 at 9:22 AM, Alfred Monticello ajmce...@yahoo.com wrote: I wouldn't have a database to compare names to, each one would essentially be unique and unknown. It's sounding like this idea may be not possible...What high end options are available? I read about lumenvox, but I believe that compares to a known list of names (such as a directory, or Yes No, Digits, etc) Hum... From: Don Kelly d...@donkelly.biz To: Asterisk Users Mailing List - Non-Commercial Discussion asterisk-users@lists.digium.com Sent: Friday, January 30, 2009 7:41:02 PM Subject: Re: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? There are solutions ranging from free to many thousands of dollars, with effectiveness ranging from nearly worthless to almost pretty good. A lot depends on your application. The most successful application would match an utterance from a known speaker to a known list of a couple dozen names. For example, if I say Alfred Monticello, the application can easily distinguish this from other list entries such as Don Kelly and Robert Smith. The least successful would attempt to convert an utterance from an unknown speaker to text (which is what your inquiry implies). Even if it clearly understands the speaker, the result could easily be Alphret Mahntichelo. --Don Don Kelly PCF Corp People Come First 651 842-1000 888 Don Kell(y) 651 842-1001 fax From:asterisk-users-boun...@lists.digium.com [mailto:asterisk-users-boun...@lists.digium.com] On Behalf Of Alfred Monticello Sent: Friday, January 30, 2009 9:25 PM To: asterisk-users@lists.digium.com Subject: [asterisk-users] Ideas on how to convert spoken name to text (orwav to text)..speech recognition software? I'm interested in taking a persons spoken recorded name (First, Last) and converting the two spoken words to text. Is there any solutions out there that would make this possible? ___ -- Bandwidth and Colocation Provided by http://www.api-digital.com -- 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 -- asterisk-users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users