This list is closed, nobody may subscribe to it.
2002 |
Jan
(29) |
Feb
(11) |
Mar
(134) |
Apr
(55) |
May
(91) |
Jun
(77) |
Jul
(46) |
Aug
(147) |
Sep
(96) |
Oct
(103) |
Nov
(130) |
Dec
(103) |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2003 |
Jan
(207) |
Feb
(132) |
Mar
(87) |
Apr
(183) |
May
(89) |
Jun
(44) |
Jul
(41) |
Aug
(22) |
Sep
(39) |
Oct
(37) |
Nov
(47) |
Dec
(8) |
2004 |
Jan
(22) |
Feb
(54) |
Mar
(52) |
Apr
(7) |
May
(47) |
Jun
(19) |
Jul
|
Aug
(43) |
Sep
(7) |
Oct
(5) |
Nov
|
Dec
|
2005 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
(3) |
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
2006 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
(1) |
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
2007 |
Jan
|
Feb
|
Mar
(1) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
(1) |
Oct
|
Nov
|
Dec
|
2008 |
Jan
|
Feb
|
Mar
(6) |
Apr
(20) |
May
|
Jun
(4) |
Jul
(2) |
Aug
(1) |
Sep
|
Oct
(17) |
Nov
(11) |
Dec
(14) |
2009 |
Jan
(3) |
Feb
(56) |
Mar
(19) |
Apr
(81) |
May
(24) |
Jun
|
Jul
|
Aug
(5) |
Sep
(57) |
Oct
(24) |
Nov
(34) |
Dec
(56) |
2010 |
Jan
(15) |
Feb
(42) |
Mar
(79) |
Apr
(45) |
May
(27) |
Jun
(41) |
Jul
(69) |
Aug
(14) |
Sep
(18) |
Oct
(19) |
Nov
(33) |
Dec
(25) |
2011 |
Jan
(4) |
Feb
(22) |
Mar
(53) |
Apr
(47) |
May
(29) |
Jun
(18) |
Jul
(18) |
Aug
(2) |
Sep
(6) |
Oct
(32) |
Nov
(18) |
Dec
|
2012 |
Jan
(8) |
Feb
(12) |
Mar
(62) |
Apr
(37) |
May
(22) |
Jun
(8) |
Jul
(3) |
Aug
(3) |
Sep
(2) |
Oct
(2) |
Nov
(28) |
Dec
(19) |
2013 |
Jan
(28) |
Feb
(24) |
Mar
(8) |
Apr
(17) |
May
(6) |
Jun
(14) |
Jul
(6) |
Aug
(5) |
Sep
(17) |
Oct
(12) |
Nov
(24) |
Dec
(16) |
2014 |
Jan
(13) |
Feb
(9) |
Mar
(2) |
Apr
(3) |
May
|
Jun
(2) |
Jul
(6) |
Aug
(6) |
Sep
(28) |
Oct
(4) |
Nov
(1) |
Dec
(4) |
2015 |
Jan
(5) |
Feb
(11) |
Mar
(6) |
Apr
(10) |
May
(9) |
Jun
(13) |
Jul
(5) |
Aug
(10) |
Sep
(13) |
Oct
(4) |
Nov
(14) |
Dec
(14) |
2016 |
Jan
(32) |
Feb
(33) |
Mar
(37) |
Apr
(6) |
May
(7) |
Jun
(11) |
Jul
(3) |
Aug
(2) |
Sep
(9) |
Oct
(11) |
Nov
(16) |
Dec
(3) |
2017 |
Jan
(3) |
Feb
(15) |
Mar
(41) |
Apr
(10) |
May
(8) |
Jun
(4) |
Jul
|
Aug
(63) |
Sep
|
Oct
(7) |
Nov
(2) |
Dec
(3) |
2018 |
Jan
|
Feb
|
Mar
(1) |
Apr
|
May
(3) |
Jun
(15) |
Jul
|
Aug
|
Sep
(2) |
Oct
(2) |
Nov
(1) |
Dec
|
2019 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(2) |
Jun
|
Jul
(1) |
Aug
(6) |
Sep
(3) |
Oct
(2) |
Nov
|
Dec
|
2020 |
Jan
|
Feb
(3) |
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(1) |
Nov
|
Dec
|
2021 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
(2) |
Dec
|
2022 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(1) |
Nov
|
Dec
|
From: James S. <jsa...@gm...> - 2022-10-21 23:53:57
|
CMUDICT has the voiced phone in the words or, for, four, and fore as the same as in the word ought. But I believe those are completely different voiced phones, differing in the constriction of the lips, or "roundedness": https://www.youtube.com/watch?v=rbiLFUu2YSU https://www.youtube.com/watch?v=0BIgydCujFY https://www.youtube.com/watch?v=TBhkYNdIhEU https://www.youtube.com/watch?v=xIeSTGKjV2o Can you please confirm this? I've noticed it in the Google Search pronunciation remediation web app you can get by googling [how to pronounce for]. Please reply to the list to let me know whether or not this makes sense. There is a marked-up version of Wikipedia 's IPA vowel chart and a spectrograph of me saying "for, ought, oh ah oh ah oh ah oh" at https://ibb.co/album/gvvVnV Thanks in advance. Best regards, Jim Salsman -- ji...@ph... Please support universal wideband audio telephony: https://bit.ly/fccaudio |
From: James S. <jsa...@gm...> - 2021-11-23 22:39:30
|
Hi Subham, There is a new version of the articulatory feature extraction system I have not released yet, but it is open source thanks to Kevin Lenzo. Are you able to follow the instructions for the earlier version on https://github.com/jsalsman/featex ? For French, you have to get a pronunciation dictionary using the closest CMUBET/ARPABET equivalents. The diphthong table at https://bit.ly/zoomphon may be of assistance. Please let me know your thoughts. Best regards, Jim Salsman Mountain View, California On Fri, Nov 12, 2021 at 10:21 AM Subham Sekhar Sahoo <su...@gm...> wrote: > > Hey all, > > I’m an incoming Ph.D. student at Cornell University. I want to use cmusphinx’s forced alignment of phonemes feature in one of my projects. I have the following 2 questions - > > 1. The website below shows how to do it for the English Language. I’d like to know how to adapt it for the French Language? > > 2. The website below says that featex should be preferred for its improved performance but it’s not obvious how to use it for this task. > > Link: https://cmusphinx.github.io/wiki/pocketsphinx_pronunciation_evaluation/ > > Warm regards, > Subham Sekhar Sahoo > _______________________________________________ > Cmusphinx-devel mailing list > Cmu...@li... > https://lists.sourceforge.net/lists/listinfo/cmusphinx-devel |
From: Subham S. S. <su...@gm...> - 2021-11-12 18:20:51
|
Hey all, I’m an incoming Ph.D. student at Cornell University. I want to use cmusphinx’s forced alignment of phonemes feature in one of my projects. I have the following 2 questions - 1. The website below shows how to do it for the English Language. I’d like to know how to adapt it for the French Language? 2. The website below says that *featex* should be preferred for its improved performance but it’s not obvious how to use it for this task. Link: https://cmusphinx.github.io/wiki/pocketsphinx_pronunciation_evaluation/ Warm regards, Subham Sekhar Sahoo |
From: amira r. <ayr...@ya...> - 2020-10-26 12:15:03
|
Hello I am a student and i want to learn CMU Speech Recognition Program and i have download the sphinx src but it does not work , it seems that are missing files.Can you please help ?Best Regards |
From: Evandro G. <eg...@gm...> - 2020-02-26 14:32:37
|
Message bounced. Please Cc sender, if you respond. --Evandro ---------- Forwarded message ---------- From: Liya Dev <li...@ou...> To: "cmu...@li..." < cmu...@li...> Cc: Bcc: Date: Wed, 26 Feb 2020 14:27:51 +0000 Subject: Regarding CMU Sphinx Model Respected Sir/Madam We are doing the voice recognition based home automation using Cmu Sphinx, in which we have trained the model but the problem is that how can we use our trained model in our python code? And how we can improve accuracy in our model please help we are students. Please request you. we hope you are help. please |
From: Nickolay S. <nsh...@gm...> - 2020-02-04 21:22:39
|
Dear Simon Thank you for keeping track on this. I admit pocketsphinx-python project exists and contributed a lot to pocketsphinx popularity, I'm grateful to Bamboocher for that. I also commented on pypi/pocketsphinx misalignment here: https://github.com/cmusphinx/sphinxbase/issues/62 <https://github.com/cmusphinx/sphinxbase/issues/62> Overall, there likely will not be any big progress on pocketsphinx soon, I'm very busy with vosk library for android and rpi, so it does not really matter which version you package. Pypi version was last updated 2 years ago too. Given most people use pypi version, you might want to package it I think. > 4 февр. 2020 г., в 23:49, simon <de...@ka...> написал(а): > > Dear Maintainers of CMUSphinx/PocketSphinx > > There was a discussion on the Debian bug tracker on which upstream to > use for the python3-pocketsphinx package. As you might have noticed, > there is a fork of the python3 bindings which is used on the PyPi > repositories, containing incompatibilities to the CMUSphinx version. > > You can see the discussion here: > https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=943646 > > I'd like to ask you for input on how to best resolve this issue: Could > someone of your team join the discussion in the Debian bug tracker > (94...@bu...) and give your opinion on how to proceed? > > Thank you very much. > > Best, Simon > > > _______________________________________________ > Cmusphinx-devel mailing list > Cmu...@li... > https://lists.sourceforge.net/lists/listinfo/cmusphinx-devel |
From: simon <de...@ka...> - 2020-02-04 21:05:47
|
Dear Maintainers of CMUSphinx/PocketSphinx There was a discussion on the Debian bug tracker on which upstream to use for the python3-pocketsphinx package. As you might have noticed, there is a fork of the python3 bindings which is used on the PyPi repositories, containing incompatibilities to the CMUSphinx version. You can see the discussion here: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=943646 I'd like to ask you for input on how to best resolve this issue: Could someone of your team join the discussion in the Debian bug tracker (94...@bu...) and give your opinion on how to proceed? Thank you very much. Best, Simon |
From: Aakash S. <Aa...@cl...> - 2019-09-13 13:48:42
|
Hello Sir/Ma'm I have use Sphinx for read voice file.during these operation voice model not reading file perfectly. i have also make language model as custom but result has been same, i have also try your suggestions from stack overflow and Sourceforge but this suggestion not working for me. please suggest me what can i do Thanks! |
From: James S. <jsa...@gm...> - 2019-09-09 16:15:41
|
Spoken Language Interest Group (SLIG) news: Please see https://phabricator.wikimedia.org/T166929#5473028 for an effort to support unconstrained keyword spotting interactions with 0.6 GB of data, including schema updates. Want to help? http://bit.ly/slig and/or https://donate.speakclearly.info. Best regards, Jim Salsman |
From: Evandro G. <eg...@gm...> - 2019-09-04 08:12:26
|
Message bounced. Evandro > ---------- Forwarded message ---------- > From: "Олег Викторович" <zco...@gm...> > To: cmu...@li... > Cc: > Bcc: > Date: Tue, 3 Sep 2019 19:12:28 +0700 > Subject: Can't download 'Acoustic and Language Models / Russian' > Hi All, > > I tried to investigate your great project, but I can't download Acoustic > and Language Models for Russian from here: > > > https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/Russian/ > > > I see only this message: > > Server Error > An error occurred. See the error logs for more information. (Turn debug on > to display exception reports here) > > Where I can download these models? > > Thanks! > > -- > Oleg > |
From: Nickolay S. <nsh...@gm...> - 2019-08-24 13:32:36
|
Shared, thank you very much, Carlos! https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/Mexican%20Spanish/ >> >> Hello Carlos >> >> Sure, share the files on dropbox/google drive and send me the link. I'll upload the model. >> >>> 24 авг. 2019 г., в 2:07, Carlos Daniel Hdz. Mena <men...@ho... <mailto:men...@ho...>> написал(а): >>> >>> Hello Nikolay, >>> >>> I have the model already train. I would like you to include it in your sourceforge list: >>> >>>> >>>> https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ <https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/> >>> >>> Is it possible? >>> >>> Carlos >>> >>> From: Nickolay Shmyrev <nsh...@gm... <mailto:nsh...@gm...>> >>> Sent: Friday, August 23, 2019 5:37 PM >>> To: Evandro Gouvea <eg...@gm... <mailto:eg...@gm...>> >>> Cc: cmusphinx-devel <cmu...@li... <mailto:cmu...@li...>>; men...@ho... <mailto:men...@ho...> <men...@ho... <mailto:men...@ho...>> >>> Subject: Re: [Cmusphinx-devel] I want to publish some acoustic models in Spanish with you >>> >>> Hello Carlos >>> >>> Sure, we can help you. What is your current problem, do you have the model already trained or you have the dataset and you need a help to train? >>> >>>> 23 авг. 2019 г., в 9:51, Evandro Gouvea <eg...@gm... <mailto:eg...@gm...>> написал(а): >>>> >>>> Folks, the message from a non-subscriber bounced back. >>>> >>>> Nickolay, you're probably the one who can help :-). >>>> >>>> --Evandro >>>> >>>> >>>> ---------- Forwarded message ---------- >>>> From: "Carlos Daniel Hdz. Mena" <men...@ho... <mailto:men...@ho...>> >>>> To: "cmu...@li... <mailto:cmu...@li...>" <cmu...@li... <mailto:cmu...@li...>> >>>> Cc: >>>> Bcc: >>>> Date: Fri, 23 Aug 2019 00:54:46 +0000 >>>> Subject: I want to publish some acoustic models in Spanish with you >>>> Hello, >>>> >>>> My name is Carlos Mena and currently I'm a postdoc at the University of Malta. >>>> >>>> I'm aware of this list of models of yours: >>>> >>>> https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ <https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/> >>>> >>>> >>>> So I would like to contribute with some PocketSphinx Acoustic Models in Mexican Spanish made out of 581 hours. >>>> >>>> Can you help me to do so??? |
From: Nickolay S. <nsh...@gm...> - 2019-08-23 23:46:36
|
Hola Basic model is available here https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/Portuguese/ For a language model one could simply use a grammar. As for better model, I can train it in a couple of weeks if you push me strong enough. I wish I had more time for Portuguese. > 23 авг. 2019 г., в 17:00, Evandro Gouvea <eg...@gm...> написал(а): > > Folks, > > Does anyone have pointers to Sphinx acoustic models (and LM?) in pt-br? > > Marcelo is asking for help, and offering a book he wrote about IoT using Sphinx (link in the other message in this thread). > > I am not aware of any, unfortunately. > > Nickolay, continua aprendendo português? :-). > > --Evandro > > > On Fri, 23 Aug 2019 at 15:35, marcelo martins <mar...@gm... <mailto:mar...@gm...>> wrote: > Alguem pode me indicar algum bom modelo em Português-BR. > Preciso de um modelo para sphinx nesta língua! > > Gostaria tambem de disponibilizar um livro que fiz em português, onde ensino IoT, apresentando o uso do sphinx. |
From: Nickolay S. <nsh...@gm...> - 2019-08-23 22:38:10
|
Hello Carlos Sure, we can help you. What is your current problem, do you have the model already trained or you have the dataset and you need a help to train? > 23 авг. 2019 г., в 9:51, Evandro Gouvea <eg...@gm...> написал(а): > > Folks, the message from a non-subscriber bounced back. > > Nickolay, you're probably the one who can help :-). > > --Evandro > > > ---------- Forwarded message ---------- > From: "Carlos Daniel Hdz. Mena" <men...@ho... <mailto:men...@ho...>> > To: "cmu...@li... <mailto:cmu...@li...>" <cmu...@li... <mailto:cmu...@li...>> > Cc: > Bcc: > Date: Fri, 23 Aug 2019 00:54:46 +0000 > Subject: I want to publish some acoustic models in Spanish with you > Hello, > > My name is Carlos Mena and currently I'm a postdoc at the University of Malta. > > I'm aware of this list of models of yours: > > https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ <https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/> > > > So I would like to contribute with some PocketSphinx Acoustic Models in Mexican Spanish made out of 581 hours. > > Can you help me to do so??? |
From: Evandro G. <eg...@gm...> - 2019-08-23 14:00:52
|
Folks, Does anyone have pointers to Sphinx acoustic models (and LM?) in pt-br? Marcelo is asking for help, and offering a book he wrote about IoT using Sphinx (link in the other message in this thread). I am not aware of any, unfortunately. Nickolay, continua aprendendo português? :-). --Evandro On Fri, 23 Aug 2019 at 15:35, marcelo martins < mar...@gm...> wrote: > Alguem pode me indicar algum bom modelo em Português-BR. > Preciso de um modelo para sphinx nesta língua! > > Gostaria tambem de disponibilizar um livro que fiz em português, onde > ensino IoT, apresentando o uso do sphinx. > > > > > Em sex, 23 de ago de 2019 às 03:52, Evandro Gouvea <eg...@gm...> > escreveu: > >> Folks, the message from a non-subscriber bounced back. >> >> Nickolay, you're probably the one who can help :-). >> >> --Evandro >> >> >> ---------- Forwarded message ---------- >> From: "Carlos Daniel Hdz. Mena" <men...@ho...> >> To: "cmu...@li..." < >> cmu...@li...> >> Cc: >> Bcc: >> Date: Fri, 23 Aug 2019 00:54:46 +0000 >> Subject: I want to publish some acoustic models in Spanish with you >> Hello, >> >> My name is Carlos Mena and currently I'm a postdoc at the University of >> Malta. >> >> I'm aware of this list of models of yours: >> >> >> https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ >> >> >> So I would like to contribute with some PocketSphinx Acoustic Models in >> Mexican Spanish made out of 581 hours. >> >> Can you help me to do so??? >> >> >> Carlos >> _______________________________________________ >> Cmusphinx-devel mailing list >> Cmu...@li... >> https://lists.sourceforge.net/lists/listinfo/cmusphinx-devel >> > |
From: marcelo m. <mar...@gm...> - 2019-08-23 13:35:46
|
https://sourceforge.net/projects/robotinics/files/livro/Projetos%20IOT%20com%20Arduino%20e%20Raspberry-rev10.pdf.zip/download Segue link do livro No outro não foi Em sex, 23 de ago de 2019 às 03:52, Evandro Gouvea <eg...@gm...> escreveu: > Folks, the message from a non-subscriber bounced back. > > Nickolay, you're probably the one who can help :-). > > --Evandro > > > ---------- Forwarded message ---------- > From: "Carlos Daniel Hdz. Mena" <men...@ho...> > To: "cmu...@li..." < > cmu...@li...> > Cc: > Bcc: > Date: Fri, 23 Aug 2019 00:54:46 +0000 > Subject: I want to publish some acoustic models in Spanish with you > Hello, > > My name is Carlos Mena and currently I'm a postdoc at the University of > Malta. > > I'm aware of this list of models of yours: > > > https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ > > > So I would like to contribute with some PocketSphinx Acoustic Models in > Mexican Spanish made out of 581 hours. > > Can you help me to do so??? > > > Carlos > _______________________________________________ > Cmusphinx-devel mailing list > Cmu...@li... > https://lists.sourceforge.net/lists/listinfo/cmusphinx-devel > |
From: Evandro G. <eg...@gm...> - 2019-08-23 06:51:38
|
Folks, the message from a non-subscriber bounced back. Nickolay, you're probably the one who can help :-). --Evandro ---------- Forwarded message ---------- From: "Carlos Daniel Hdz. Mena" <men...@ho...> To: "cmu...@li..." < cmu...@li...> Cc: Bcc: Date: Fri, 23 Aug 2019 00:54:46 +0000 Subject: I want to publish some acoustic models in Spanish with you Hello, My name is Carlos Mena and currently I'm a postdoc at the University of Malta. I'm aware of this list of models of yours: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/ So I would like to contribute with some PocketSphinx Acoustic Models in Mexican Spanish made out of 581 hours. Can you help me to do so??? Carlos |
From: James S. <jsa...@gm...> - 2019-07-13 22:03:06
|
I wish I was faster at finding these. Does anyone have a list of all of them? for F AO UH R also faure, fore, forr, four # NON-CMUDICT (NO DIPHTHONGS) live L IH V also liv # BAD HOMOGRAPH -- CHECK EXEMPLARS our AW ER also hour # CMUDICT? piano P IY AE N AO UH # CMUDICT? read R IY D also reed # BAD HOMOGRAPH -- CHECK EXEMPLARS the DH AH # won a poll BAD HOMOGRAPH More homophones and homographs at https://phabricator.wikimedia.org/T166929#5330538 Best regards, Jim |
From: James S. <jsa...@gm...> - 2019-05-11 16:34:00
|
I've begun forming a Spoken Language Interest Group at the IEEE, and with associates and colleagues researching and teaching language, and speech recognition engineers interested in pronunciation assessment: http://j.mp/slig We are passing the hat to commission additional data collection and keep building free pronunciation remediation applications: http://wefunder.com/speakclearly The question of whether intelligibility is a cultural construct is similar to the question of whether opinions are objective in aggregate. The phonological control standard for English from the Common European Framework of Reference states that intelligibility is more fundamental than accent intonation and phonological stress. Please join! We have had nine sign-ups in the first four days since the Group was announced at the Learning Technology Standards Committee. I am happy to answer any questions on- or off-list. Best regards, Jim |
From: sumeet c. <sum...@gm...> - 2019-05-01 16:57:08
|
hi i am trying to build java speech recognition project.i have imported the the two jar files but i am getting an error while compiling error: Caused by: java.lang.ClassNotFoundException: edu.cmu.sphinx.api.Configuration at java.base/jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:583) at java.base/jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:178) at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:521) ... 1 more can you please help me out i am very keen to learn Sumeet Chandel sum...@gm... 9911634383 |
From: adnan a. <adn...@uo...> - 2018-11-07 05:56:56
|
Is there any one who can guide me in this regards. Thanks in advance. On Wed, Oct 31, 2018 at 5:22 PM adnan ali <adn...@uo...> wrote: > Dear All > I hope you all are doing well in your life. > I have experience with acoustic modeling and I am aware of it, now I want > to work with Speaker Identification but I am not able to analyse, from > where I should start. > I ran the speaker identification example of sphinx4 although I am having > errors. But it seems to me it is more about speaker Identification at java > level not at feature level. > > Long story short. > Does CMUSphinx supports speaker identification e.g getting speaker > specific features? > If yes, then from where to start, > If no, then any other suitable tool for this? > Thanking in anticipation > > > -- > *Regards* > > *Adnan Ali * <https://www.facebook.com/MhAdnanAli> > Associate Lecturer > *Department of Information Technology * > *University of Gujrat (Sialkot Sub-Campus-PPP**)* > Daska Road, Sialkot, Pakistan > Site: https://sites.google.com/view/adnan-ali > > -- *Regards* *Adnan Ali * <https://www.facebook.com/MhAdnanAli> Associate Lecturer *Department of Information Technology * *University of Gujrat (Sialkot Sub-Campus-PPP**)* Daska Road, Sialkot, Pakistan Site: https://sites.google.com/view/adnan-ali |
From: adnan a. <adn...@uo...> - 2018-10-31 12:50:46
|
Dear All I hope you all are doing well in your life. I have experience with acoustic modeling and I am aware of it, now I want to work with Speaker Identification but I am not able to analyse, from where I should start. I ran the speaker identification example of sphinx4 although I am having errors. But it seems to me it is more about speaker Identification at java level not at feature level. Long story short. Does CMUSphinx supports speaker identification e.g getting speaker specific features? If yes, then from where to start, If no, then any other suitable tool for this? Thanking in anticipation -- *Regards* *Adnan Ali * <https://www.facebook.com/MhAdnanAli> Associate Lecturer *Department of Information Technology * *University of Gujrat (Sialkot Sub-Campus-PPP**)* Daska Road, Sialkot, Pakistan Site: https://sites.google.com/view/adnan-ali |
From: Evandro G. <eg...@gm...> - 2018-10-15 06:46:40
|
Message got sent to the wrong list by a non subscriber. Please Cc sender. Evandro ---------- Forwarded message --------- From: <cmu...@li...> Date: Mon 15. Oct 2018 at 05:41 Subject: Cmusphinx-news post from jav...@gm... requires approval To: <cmu...@li...> ---------- Forwarded message ---------- From: Javeria Naveed <jav...@gm...> To: cmu...@li... Cc: Bcc: Date: Mon, 15 Oct 2018 08:40:50 +0500 Subject: Fwd: Voice features extraction Hey, i am new to sphinx and working on speaker identification project. I am facing problems in features extraction E.g mfcc coeffecients and pitch extraction of voice ,, Can someone help me out from where to start ,, Is there any feature in training of data which can help me extraction ???? |
From: Evandro G. <eg...@gm...> - 2018-09-18 11:39:35
|
Folks, The message below was sent by a non-subscriber and bounced back. Please Cc senders when responding. --Evandro Gouvea ---------- Forwarded message ---------- From: Suresh S <Sur...@la...> To: "cmu...@li..." < cmu...@li...> Cc: Anand Mn <ANA...@la...>, Ivin Sam < Ivi...@la...>, Nithish D <Nit...@la...>, Maruthi Rudresh <Mar...@la...> Bcc: Date: Tue, 18 Sep 2018 10:49:36 +0000 Subject: HFDF//SPEECH TRANSCRIPTION Dear Sir, For one of our project, we need Speech to Text (audio transcription) software. This software should be standalone and all the libraries should be inbuilt with the option to upgrade manually (server or client). Below Language support from Audio to Text is required:- (a) Mandarin,(b) Cantonese (c) Bhasha Indonesia, (d) Sinhala, (e) Thai, (f) Arabic, (g)Persian, (h)Bhasha Malay, U)Divehi, (k) Pashto, (!)Burmese, (m)Balluchi, (n) Brahui, (p) Vietnamese (q) French. Manual or auto feed option to be provided and software support for the next 10 years required. This system expected to be on a standalone system and will not be connected to internet. Can you help us for the above requirement on paid basis. You may please send us the feasibility and your charges for this requirement. *Best Regards,* ಸುರೇಶ್ ಸಂಜೀವ */ Suresh Sanjeev* sur...@la... / +91.8892644264 *LARSEN AND TOUBRO LIMITED* 145/2,Komarla Solitaire, Old Madras Road,CV Raman Nagar, Bengaluru-560093 Office: +91.80.66936221 / Fax: +91.80.66936333 http://www.larsentoubro.com/ [image: cid:image001.png@01D44F68.C70602C0] <https://www.linkedin.com/in/sureshsanjeev> *Larsen & Toubro Limited * *www.larsentoubro.com <http://www.larsentoubro.com>* This Email may contain confidential or privileged information for the intended recipient (s). If you are not the intended recipient, please do not use or disseminate the information, notify the sender and delete it from your system. |
From: PANKAJ B. <pan...@du...> - 2018-09-09 11:05:36
|
Hello all. Organisations can now start applying to Google CodeIn program <https://codein.withgoogle.com/>. It would be very beneficial for CMUSphinx as a lot of small but long due tasks can be completed by young students and it also helps the community grow and prosper. We had tried last year as well, so we already have over 25 tasks in a Google sheets somewhere. (Found it! <https://docs.google.com/spreadsheets/d/1yK_isyTqbinz4tGryx86tsW9yP4ojutUqsiZJG88TmI/edit?usp=sharing> ) We should definitely try again and try to do better this time. Thanks Pankaj |
From: Kevin L. <kev...@gm...> - 2018-06-30 23:54:13
|
I’m sorry my work from 20 years ago is not giving you what you need to run basic scripts and improve the resources to advance here. Cheers, Kevin > On Jun 30, 2018, at 7:47 PM, Kevin Lenzo <kev...@gm...> wrote: > > You have always been one of the good ones. > > Kevin > >> On Jun 30, 2018, at 6:23 PM, James Salsman <jsa...@gm...> wrote: >> >> Dr. Rudnicky, >> >> If I had a command-and-control and/or dictation test suite I would >> measure the empirical question myself, but I don't, so I hope you, or >> anyone here who does have such test suites, will take a closer look at >> the question. I've never been interested in command-and-control or >> dictation. There are (more labor-intensive?) ways to measure the >> change for synthesis, too, which would be absolutely necessary along >> with the other aspects Kevin mentioned, before changing it for >> everyone. >> >> Dr. Horacio Franco at SRI, after having set the formula for "Goodness >> of Pronunciation" (often "GoP") around 1996 with Drs. Jared Bernstein >> et al., which was taken up in turn by Prof. Steve Young's group at >> Cambridge e.g. in Dr. Silke Witt's 1999/2000 thesis, is now >> contemplating extraction of articulatory features early in the signal >> processing path: >> https://www.researchgate.net/publication/325570699_Articulatory_Features_for_ASR_of_Pathological_Speech >> >> We really need to help everyone who ever used that formula, which I >> suspect has a physical units' type mismatch error, because of larger >> societal effects such as these: >> >> https://www.theguardian.com/australia-news/2017/aug/08/computer-says-no-irish-vet-fails-oral-english-test-needed-to-stay-in-australia >> >> https://www.ft.com/content/dc7faee2-51e5-11e8-b3ee-41e0209208ec >> >> These are very serious manifestations of a software bug, affecting the >> immigration status of tens of thousands of people. >> >> Best regards, >> Jim >> >>> On Sat, Jun 30, 2018 at 4:13 PM, Alexander Rudnicky <ai...@cs...> wrote: >>> Uh, I have been maintaining it, more or less. It's now at (I think) version 0.7b. The versions get bumped whenever I feel I've put in some big chunk of fixing. There's minor maintenance ongoing. >>> >>> Apart from adding words (harvested from words that show up in lmtool uploads that are backed off to LtoS, making sure that the 10k most-frequent words are in there, cleaning out some of the crap, etc) and fixing stuff people send in. I occasionally put time into regularizations of one kind or another. Also, trying to figure out how to deal with Nickolay's bootleg version. And so on. >>> >>> I've had to fix your script at http://www.speech.cs.cmu.edu/cgi-bin/cmudict, since perl had evolved too much. >>> >>> There are also ongoing requests for the same resource in other languages (e.g. Spanish). Someday. >>> >>> It's been more or less on a hobby level, though at some point I did put together an NSF proposal to get more (people) resources for it. But then got busy with some other stuff. I should get back top that... >>> >>> Alex >>> >>> >>> >>> >>> -----Original Message----- >>> From: Kevin Lenzo <kev...@gm...> >>> Sent: Saturday, June 30, 2018 5:15 PM >>> To: Alexander Rudnicky <ai...@cs...> >>> Cc: James Salsman <jsa...@gm...>; cmusphinx-devel <cmu...@li...> >>> Subject: Re: [Cmusphinx-devel] diphthong removal >>> >>> Just following up here, I wish this really important resource would be updated. CMU did something really important here, and it is still use A LOT, but hasn’t seen a serious consideration and version update in almost 20 years. It would be nice if CMU recognized its leadership here and really pushed ahead with publicly available lexica. >>> >>> oak >>> >>>> On Jun 30, 2018, at 4:29 PM, Kevin Lenzo <kev...@gm...> wrote: >>>> >>>> Hi Alex, >>>> >>>> I’m sure you’re aware that the CMU Pronouncing Dictionary is used for more than ASR. For example, Festival and FestVox both use it, and many voices available on Android today come from that. >>>> >>>> If we are considering changes to the dictionary itself, it is worth considering the linguistic value, as well as the multiple clients of this data. To make such a change would have unnecessary impact on these downstream uses of the data, favoring one perhaps temporary result of a particular client’s application. >>>> >>>> Do whatever you want with the data — that’s the whole point of the liberal licensing scheme; but consider carefully the impact on the overall use and importance of the fundamental resource. >>>> >>>> oak >>>> >>>>> On Jun 30, 2018, at 10:16 AM, Alexander Rudnicky <ai...@cs...> wrote: >>>>> >>>>> Folks, >>>>> >>>>> Cmudict is intended for use in ASR. The set of phonetic units evolved to fit that need. The original phone set had stuff like DX, the dental flap, that eventually disappeared. An important reason was the realization that context is highly predictive of phonetic realization and that it's not necessary to explicitly code allophones (assuming you can even to it right). >>>>> >>>>> The diphthong issue is a bit different of course. I would hazard that the diphthong provides a better context scope for reco. So diphthongs might still be useful as a unit. To me this seems enough of a reason. But acoustic modeling has evolved. So who knows? >>>>> >>>>> I agree with James, though. It's an empirical question. Try it both ways and see what happens. There is also TTS and other applications that might benefit; ideally there's a deterministic mapping from the base ASR representation to the others. >>>>> >>>>> Alex >>>>> >>>>> -----Original Message----- >>>>> From: James Salsman <jsa...@gm...> >>>>> Sent: Saturday, June 30, 2018 9:54 AM >>>>> To: cmusphinx-devel <cmu...@li...>; Kevin >>>>> Lenzo <kev...@gm...> >>>>> Subject: Re: [Cmusphinx-devel] diphthong removal >>>>> >>>>> Kevin, >>>>> >>>>> Thank you for your reply. Your name is still at the bottom of the CMUDICT page, so I figure it's worth as much trying to convince you of this, whether I end up using it locally or otherwise. >>>>> >>>>>> In IPA, the diphthongs are indicated by a tie marker. [Replacing >>>>>> them with consecutive phonemes] loses information >>>>> >>>>> I would like to measure how much information is involved there. I'm not convinced it's positive. It's certainly much smaller than the amount of information available from nondiphthong phonemes about which diphones a learner is able to articulate. >>>>> >>>>> There is a physiological argument that diphthongs, as the only nonstationary articulations, are transitions instead of positions in articulation space. Whether this actually provides information is very questionable, because such data compression is either lossy or lossless, not enhancing. Therefore at best, no information could be added. Such coding mistakes are common in natural languages. >>>>> >>>>> However, the /ʊ/ vs. /ɜ/, /ɛ/ vs. /e/, /ɔ/ and /o/ substitutions available in the phoneme set would unquestionably represent a loss of some information, and I'd like to figure out how to measure how much. >>>>> I think it's pretty easy -- just make two -dict's and measure the relative accuracy, speed, etc. on some sufficiently broad test suite. >>>>> People on this list do that kind of thing all the time, right? >>>>> >>>>> Best regards, >>>>> Jim >>>>> >>>>>> On Fri, Jun 29, 2018 at 7:26 PM, Kevin Lenzo <kev...@gm...> wrote: >>>>>> James, >>>>>> >>>>>> I don’t control this or update it these days, but there are phonological reasons for not doing this in the dictionary. There is a significant phonetic distinction between a diphthong and two consecutive phones. In IPA, the diphthongs are indicated by a tie marker. Your suggestion loses information and so is not a good idea for the general dictionary. >>>>>> >>>>>> Kevin >>>>>> >>>>>>> On Jun 29, 2018, at 4:13 PM, James Salsman <jsa...@gm...> wrote: >>>>>>> >>>>>>> Kevin, >>>>>>> >>>>>>> I need to use diphones for learner analytics to complete >>>>>>> http://j.mp/irslides >>>>>>> >>>>>>> How do you feel about eliminating diphthongs from CMUDICT? >>>>>>> >>>>>>> AW -> AA UH >>>>>>> AY -> AA IY >>>>>>> ER -> UH R (substitutes /ʊ/ for /ɜ/) EY -> EH IY (substitutes /ɛ/ >>>>>>> for /e/) OW -> AO UH (substitutes /ɔ/ for /o/) OY -> AO IY >>>>>>> >>>>>>> I'm going to do it, locally in something called Cloud Firestore >>>>>>> anyway, but I wonder whether there are any good reasons to support >>>>>>> diphthongs at all. Like ligatures in typography, a lot of simple >>>>>>> algorithms don't stay simple if they need to process the composites. >>>>>>> And it's certainly less elegant and less parsimonious, and probably >>>>>>> a violation of some rule of normal forms to support them. >>>>>>> >>>>>>> Best regards, >>>>>>> Jim >>>>> >>>>> --------------------------------------------------------------------- >>>>> --------- Check out the vibrant tech community on one of the world's >>>>> most engaging tech sites, Slashdot.org! http://sdm.link/slashdot >>>>> _______________________________________________ >>>>> Cmusphinx-devel mailing list >>>>> Cmu...@li... >>>>> https://lists.sourceforge.net/lists/listinfo/cmusphinx-devel >>> |