Menu
▾
▴
hts-engine-users — For users.
You can subscribe to this list here.
| 2008 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
(4) |
Aug
(21) |
Sep
(14) |
Oct
|
Nov
(5) |
Dec
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2009 |
Jan
|
Feb
|
Mar
|
Apr
(18) |
May
(15) |
Jun
|
Jul
|
Aug
(1) |
Sep
(15) |
Oct
(6) |
Nov
(4) |
Dec
|
| 2010 |
Jan
(11) |
Feb
|
Mar
(2) |
Apr
(3) |
May
(4) |
Jun
(1) |
Jul
|
Aug
(2) |
Sep
|
Oct
|
Nov
(3) |
Dec
(6) |
| 2011 |
Jan
(5) |
Feb
(6) |
Mar
(4) |
Apr
(5) |
May
|
Jun
(4) |
Jul
(2) |
Aug
|
Sep
|
Oct
(1) |
Nov
(2) |
Dec
(5) |
| 2012 |
Jan
(8) |
Feb
(1) |
Mar
|
Apr
|
May
(4) |
Jun
(1) |
Jul
|
Aug
(2) |
Sep
(2) |
Oct
|
Nov
|
Dec
(5) |
| 2013 |
Jan
(1) |
Feb
(12) |
Mar
(5) |
Apr
(1) |
May
(8) |
Jun
(3) |
Jul
(2) |
Aug
(4) |
Sep
|
Oct
|
Nov
(1) |
Dec
(5) |
| 2014 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
(4) |
Aug
(1) |
Sep
(1) |
Oct
(1) |
Nov
(1) |
Dec
(3) |
| 2015 |
Jan
|
Feb
|
Mar
(1) |
Apr
(1) |
May
|
Jun
|
Jul
|
Aug
(3) |
Sep
|
Oct
|
Nov
|
Dec
(4) |
| 2016 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
(5) |
| 2017 |
Jan
(1) |
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(5) |
Nov
|
Dec
(3) |
| 2018 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
(6) |
|
From: <hts...@li...> - 2018-12-28 15:32:14
|
Hi,
According HTS document I have trained successfully a 48K model(.htsvoice, and flite+hts_engline had synthesised a success voice),
but when I trained a 16K model, the synthesised voice is is completely wrong.
In HTS-demo_CMU-ARCTIC-SLT dir, I add a sample frequence parameter to run ./configure as:
./configure SAMPFREQ=16000 --with-fest-search-path=/usr/local/festival/examples \
--with-sptk-search-path=/usr/local/SPTK-3.9/bin \
--with-hts-search-path=/usr/local/HTS-2.3_for_HTK-3.4.1/bin \
--with-hts-engine-search-path=/usr/local/hts_engine_API-1.10/bin
Does it need changed other parameters?
At 2018-12-24 16:33:25, "ljh_dev" <lj...@12...> wrote:
How to training cmu model with 16kHz data? I can see any document in http://hts.sp.nitech.ac.jp/
Thanks.
在 2018-12-20 11:40:07，hts...@li... 写道：
>Hi,
>
>Although 16kHz HTS voice is not released, you can train it by running
>HTS demo scripts with 16kHz data.
>http://hts.sp.nitech.ac.jp/
>
>Regards,
>Keiichiro Oura
>
>2018年12月20日(木) 12:32 <hts...@li...>:
>>
>> Hi,
>> The sampling frequency of HTS voice version 1.06 model "cmu_us_arctic_slt.htsvoice" is 48000,
>> is there a model with a sampling frequency is 16000?
>>
>>
>>
>>
>>
>>
>>
>>
>> _______________________________________________
>> Hts-engine-users mailing list
>> Hts...@li...
>> https://lists.sourceforge.net/lists/listinfo/hts-engine-users
>
>
>_______________________________________________
>Hts-engine-users mailing list
>Hts...@li...
>https://lists.sourceforge.net/lists/listinfo/hts-engine-users
|
|
From: <hts...@li...> - 2018-12-24 08:33:38
|
How to training cmu model with 16kHz data? I can see any document in http://hts.sp.nitech.ac.jp/ Thanks. 在 2018-12-20 11:40:07，hts...@li... 写道： >Hi, > >Although 16kHz HTS voice is not released, you can train it by running >HTS demo scripts with 16kHz data. >http://hts.sp.nitech.ac.jp/ > >Regards, >Keiichiro Oura > >2018年12月20日(木) 12:32 <hts...@li...>: >> >> Hi, >> The sampling frequency of HTS voice version 1.06 model "cmu_us_arctic_slt.htsvoice" is 48000, >> is there a model with a sampling frequency is 16000? >> >> >> >> >> >> >> >> >> _______________________________________________ >> Hts-engine-users mailing list >> Hts...@li... >> https://lists.sourceforge.net/lists/listinfo/hts-engine-users > > >_______________________________________________ >Hts-engine-users mailing list >Hts...@li... >https://lists.sourceforge.net/lists/listinfo/hts-engine-users |
|
From: <hts...@li...> - 2018-12-20 03:40:24
|
Hi, Although 16kHz HTS voice is not released, you can train it by running HTS demo scripts with 16kHz data. http://hts.sp.nitech.ac.jp/ Regards, Keiichiro Oura 2018年12月20日(木) 12:32 <hts...@li...>: > > Hi, > The sampling frequency of HTS voice version 1.06 model "cmu_us_arctic_slt.htsvoice" is 48000, > is there a model with a sampling frequency is 16000? > > > > > > > > > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users |
|
From: <hts...@li...> - 2018-12-20 03:32:05
|
Hi, The sampling frequency of HTS voice version 1.06 model "cmu_us_arctic_slt.htsvoice" is 48000, is there a model with a sampling frequency is 16000? |
|
From: <hts...@li...> - 2018-12-11 12:40:33
|
Hi, HTS voice version 1.06 in http://hts-engine.sourceforge.net/ can be used. Regards, Keiichiro Oura 2018年12月11日(火) 16:49 <hts...@li...>: > > Hi, > Where can get a english htsvoice file that already trained and can be directly used? > It can run by flite_hts_engine and design it by -m parameter. > > > > > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users |
|
From: <hts...@li...> - 2018-12-11 07:49:45
|
Hi, Where can get a english htsvoice file that already trained and can be directly used? It can run by flite_hts_engine and design it by -m parameter. |
|
From: <hts...@li...> - 2017-12-25 14:36:20
|
We plan to release the next version of hts_engine API after spring 2018. Best regards, Keiichi Tokuda in behalf of HTS Working Group to...@ni... http://www.sp.nitech.ac.jp/~tokuda/ |
|
From: <hts...@li...> - 2017-12-25 14:31:26
|
We are please to inform you the release of our software
Speech Signal Processing Toolkit (SPTK) version 3.11
release December 25, 2017
for speech signal processing. We apologize if you receive multiple
copies. Please check
http://sp-tk.sourceforge.net/
Furthermore, the repository website of the next version (under
construction) is now available.
https://github.com/sp-nitech/SPTK
We would appreciate it if you would distribute this email to anyone
who would be interested in this software.
Best regards,
Keiichi Tokuda
in behalf of SPTK Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2017-12-25 14:29:38
|
We are please to inform you the release of
The HMM/DNN-based Speech Synthesis System (HTS)
version 2.3.2 release December 25, 2017
for HMM-based speech synthesis. We apologize if you receive multiple
copies. Please check
http://hts.sp.nitech.ac.jp/
Trajectory training considering global variance based on DNN and
speaker adaptive training for DNN were added.
We would appreciate it if you would distribute this email to anyone
who would be interested in this software toolkit.
Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2017-10-18 18:32:34
|
Hi,
Thanks for your help, i think my htsvoice is broken.
Regards,Nadia Mansouri.
Le Mardi 17 octobre 2017 2h13, "hts...@li..." <hts...@li...> a écrit :
Hi,
It seems that these version are ok.
Can you use released htsvoice? http://downloads.sourceforge.net/hts-engine/hts_voice_cmu_us_arctic_slt-1.06.tar.gz
If released htsvoice can be used, your htsvoice is broken.So, please check whether htsvoice is correctly generated or not.
Regards,Keiichiro Oura
2017-10-17 2:53 GMT+09:00 hts-engine-users--- via Hts-engine-users <hts...@li...>:
Hi
l'm using HTS-2.3_for_HTK-3.4.1 and hts_engine_API-1.10
Regards,
Nadia Mansouri.
Le Lundi 16 octobre 2017 17h34, "hts-engine-users@lists. sourceforge.net" <hts-engine-users@lists. sourceforge.net> a écrit :
Hi,
What HTS/hts_engine version do you use?
Regards,Keiichiro Oura
2017-10-13 0:33 GMT+09:00 hts-engine-users--- via Hts-engine-users <hts-engine-users@lists. sourceforge.net>:
Hi,I’m training the HTS-demo_CMU-ARCTIC-SLT with my own data(raw files, label files and question files), in the beginning everyting seemsok, but at the stage of synthesizing waveforms using hts_engine a problem comeout which is :
============================== ============================== =====================
Start synthesizing waveforms using hts_engine at خ أكت 1216:11:06 CET 2017
============================== ============================== =====================
Synthesizing a speech waveform from/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/data/labels/gen/ alice01.lab usinghts_engine...Error: HTS voices cannot be loaded.
Error in /usr/local/bin/hts_engine -m/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/voices/qst001/ver1/ cmu_us_arctic_slt.htsvoice -or /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.raw-ow /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.wav-ot /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.trace/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/data/labels/gen/ alice01.lab
How can i solve thisproblem, thank you for your help in advance.
| | Garanti sans virus. www.avast.com |
------------------------------ ------------------------------ ------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
______________________________ _________________
Hts-engine-users mailing list
Hts-engine-users@lists. sourceforge.net
https://lists.sourceforge.net/ lists/listinfo/hts-engine- users
------------------------------ ------------------------------ ------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot______________________________ _________________
Hts-engine-users mailing list
Hts-engine-users@lists. sourceforge.net
https://lists.sourceforge.net/ lists/listinfo/hts-engine- users
------------------------------ ------------------------------ ------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
______________________________ _________________
Hts-engine-users mailing list
Hts-engine-users@lists. sourceforge.net
https://lists.sourceforge.net/ lists/listinfo/hts-engine- users
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot_______________________________________________
Hts-engine-users mailing list
Hts...@li...
https://lists.sourceforge.net/lists/listinfo/hts-engine-users
|
|
From: <hts...@li...> - 2017-10-17 00:12:54
|
Hi, It seems that these version are ok. Can you use released htsvoice? http://downloads.sourceforge.net/hts-engine/hts_voice_cmu_us_arctic_slt-1.06.tar.gz If released htsvoice can be used, your htsvoice is broken. So, please check whether htsvoice is correctly generated or not. Regards, Keiichiro Oura 2017-10-17 2:53 GMT+09:00 hts-engine-users--- via Hts-engine-users < hts...@li...>: > > Hi > > l'm using HTS-2.3_for_HTK-3.4.1 and hts_engine_API-1.10 > > Regards, > Nadia Mansouri. > > > Le Lundi 16 octobre 2017 17h34, "hts...@li..." < > hts...@li...> a écrit : > > > Hi, > > What HTS/hts_engine version do you use? > > Regards, > Keiichiro Oura > > > > 2017-10-13 0:33 GMT+09:00 hts-engine-users--- via Hts-engine-users < > hts...@li...>: > > > > Hi, > I’m training the HTS-demo_CMU-ARCTIC-SLT with my own data (raw files, > label files and question files), in the beginning everyting seems ok, but > at the stage of synthesizing waveforms using hts_engine a problem come out > which is : > > > ============================== ============================== > ===================== > Start synthesizing waveforms using hts_engine at خ أكت 12 16:11:06 CET 2017 > ============================== ============================== > ===================== > > Synthesizing a speech waveform from /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/data/labels/gen/ alice01.lab using hts_engine...Error: HTS > voices cannot be loaded. > Error in /usr/local/bin/hts_engine -m /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/voices/qst001/ver1/ cmu_us_arctic_slt.htsvoice -or > /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ > hts_engine/alice01.raw -ow /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.wav -ot > /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ > hts_engine/alice01.trace /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/data/labels/gen/ alice01.lab > > > How can i solve this problem, thank you for your help in advance. > > > <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail> Garanti > sans virus. www.avast.com > <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail> > <https://mail.yahoo.com/?soc_src=mail&soc_trk=ma#m_-5375861877091430507_DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2> > > ------------------------------ ------------------------------ > ------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > ______________________________ _________________ > Hts-engine-users mailing list > Hts-engine-users@lists. sourceforge.net > <Hts...@li...> > https://lists.sourceforge.net/ lists/listinfo/hts-engine- users > <https://lists.sourceforge.net/lists/listinfo/hts-engine-users> > > > ------------------------------------------------------------ > ------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users > > > > ------------------------------------------------------------ > ------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users > > |
|
From: <hts...@li...> - 2017-10-16 18:03:50
|
Hi
l'm using HTS-2.3_for_HTK-3.4.1 and hts_engine_API-1.10
Regards,
Nadia Mansouri.
Le Lundi 16 octobre 2017 17h34, "hts...@li..." <hts...@li...> a écrit :
Hi,
What HTS/hts_engine version do you use?
Regards,Keiichiro Oura
2017-10-13 0:33 GMT+09:00 hts-engine-users--- via Hts-engine-users <hts...@li...>:
Hi,I’m training the HTS-demo_CMU-ARCTIC-SLT with my own data(raw files, label files and question files), in the beginning everyting seemsok, but at the stage of synthesizing waveforms using hts_engine a problem comeout which is :
============================== ============================== =====================
Start synthesizing waveforms using hts_engine at خ أكت 1216:11:06 CET 2017
============================== ============================== =====================
Synthesizing a speech waveform from/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/data/labels/gen/ alice01.lab usinghts_engine...Error: HTS voices cannot be loaded.
Error in /usr/local/bin/hts_engine -m/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/voices/qst001/ver1/ cmu_us_arctic_slt.htsvoice -or /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.raw-ow /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.wav-ot /home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/gen/qst001/ver1/ hts_engine/alice01.trace/home/nadia/T/HTS-demo_CMU- ARCTIC-SLT/data/labels/gen/ alice01.lab
How can i solve thisproblem, thank you for your help in advance.
| | Garanti sans virus. www.avast.com |
------------------------------ ------------------------------ ------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
______________________________ _________________
Hts-engine-users mailing list
Hts-engine-users@lists. sourceforge.net
https://lists.sourceforge.net/ lists/listinfo/hts-engine- users
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot_______________________________________________
Hts-engine-users mailing list
Hts...@li...
https://lists.sourceforge.net/lists/listinfo/hts-engine-users
|
|
From: <hts...@li...> - 2017-10-16 16:33:53
|
Hi, What HTS/hts_engine version do you use? Regards, Keiichiro Oura 2017-10-13 0:33 GMT+09:00 hts-engine-users--- via Hts-engine-users < hts...@li...>: > > > Hi, > I’m training the HTS-demo_CMU-ARCTIC-SLT with my own data (raw files, > label files and question files), in the beginning everyting seems ok, but > at the stage of synthesizing waveforms using hts_engine a problem come out > which is : > > > ============================================================ > ===================== > Start synthesizing waveforms using hts_engine at خ أكت 12 16:11:06 CET 2017 > ============================================================ > ===================== > > Synthesizing a speech waveform from /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/data/labels/gen/alice01.lab using hts_engine...Error: HTS > voices cannot be loaded. > Error in /usr/local/bin/hts_engine -m /home/nadia/T/HTS-demo_CMU- > ARCTIC-SLT/voices/qst001/ver1/cmu_us_arctic_slt.htsvoice -or > /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.raw > -ow /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.wav > -ot /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.trace > /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/data/labels/gen/alice01.lab > > > How can i solve this problem, thank you for your help in advance. > > > <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail> Garanti > sans virus. www.avast.com > <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail> > <#m_-5375861877091430507_DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2> > > ------------------------------------------------------------ > ------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users > > |
|
From: <hts...@li...> - 2017-10-12 15:53:52
|
Hi, I’m training the HTS-demo_CMU-ARCTIC-SLT with my own data(raw files, label files and question files), in the beginning everyting seemsok, but at the stage of synthesizing waveforms using hts_engine a problem comeout which is : ================================================================================= Start synthesizing waveforms using hts_engine at خ أكت 1216:11:06 CET 2017 ================================================================================= Synthesizing a speech waveform from/home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/data/labels/gen/alice01.lab usinghts_engine...Error: HTS voices cannot be loaded. Error in /usr/local/bin/hts_engine -m/home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/voices/qst001/ver1/cmu_us_arctic_slt.htsvoice -or /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.raw-ow /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.wav-ot /home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/hts_engine/alice01.trace/home/nadia/T/HTS-demo_CMU-ARCTIC-SLT/data/labels/gen/alice01.lab How can i solve thisproblem, thank you for your help in advance. | | Garanti sans virus. www.avast.com | |
|
From: <hts...@li...> - 2017-01-21 06:45:40
|
Hi, I have trained HTS-demo_CMU-ARCTIC-SLT model and it has successfully generated all directories like voices/, gen/ etc. Now how can I use this model to generate new sounds using hts_engine API? I am told that I can use voices/ folder for this purpose. Below are the list of files in voices folder > cmu_us_arctic_slt.htsvoice > dur.pdf > gv-lf0.pdf > gv-mgc.pdf > lf0.pdf > lf0.win1 > lf0.win2 > lf0.win3 > lpf.pdf > lpf.win1 > mgc.pdf > mgc.win1 > mgc.win2 > mgc.win3 > tree-dur.inf > tree-gv-lf0.inf > tree-gv-mgc.inf > tree-lf0.inf > tree-lpf.inf > tree-mgc.inf |
|
From: <hts...@li...> - 2016-12-26 13:36:46
|
We are please to inform you the release of our software
Speech Signal Processing Toolkit (SPTK) version 3.10
release December 25, 2016
for speech signal processing. We apologize if you receive multiple
copies. Please check
http://sp-tk.sourceforge.net/
We would appreciate it if you would distribute this email to anyone
who would be interested in this software.
Best regards,
Keiichi Tokuda
in behalf of SPTK Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2016-12-26 13:35:33
|
We are please to inform you the release of
Flite+hts_engine version 1.07
release December 25, 2016
for HMM-based speech synthesis. We apologize if you receive multiple
copies. Please check
http://hts-engine.sourceforge.net/
We would appreciate it if you would distribute this email to anyone
who would be interested in this software.
Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2016-12-26 13:34:13
|
We are please to inform you the release of
The HMM-based Speech Synthesis System (HTS)
version 2.3.1 release December 25, 2016
for HMM-based speech synthesis. We apologize if you receive multiple
copies. Please check
http://hts.sp.nitech.ac.jp/
One of new features is a DNN-based demo script.
We would appreciate it if you would distribute this email to anyone
who would be interested in this software toolkit.
Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2016-12-14 11:17:36
|
Hello, there is an how to here : https://ubuntuforums.org/showthread.php?t=2271517 Kind regards, Sébastien On Wed, Dec 14 2016 (10:12), hts...@li... wrote: > can any one suggest a good link for integrating hts in flite > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, SlashDot.org! http://sdm.link/slashdot_______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users -- Dr. Sébastien Le Maguer Postdoctorate researcher Saarland University Campus C7.4 - room 2.03 D-66123 Saarbrücken Germany phone : +49-681-302-70030 Mail: sle...@co... website : http://www.coli.uni-saarland.de/~slemaguer/ |
|
From: <hts...@li...> - 2016-12-14 09:12:59
|
can any one suggest a good link for integrating hts in flite |
|
From: <hts...@li...> - 2015-12-27 13:16:36
|
We are please to inform you the release of our software
Speech Signal Processing Toolkit (SPTK) version 3.9
release December 25, 2015
for speech signal processing. We apologize if you receive multiple
copies. Please check
http://sp-tk.sourceforge.net/
We would appreciate it if you would distribute this email to anyone
who would be interested in this software.
Best regards,
Keiichi Tokuda
in behalf of SPTK Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2015-12-27 13:14:25
|
We are please to inform you the release of
The hts_engine API version 1.10
release December 25, 2015
for HMM-based speech synthesis. We apologize if you receive multiple
copies. Please check
http://hts-engine.sourceforge.net/
We would appreciate it if you would distribute this email to anyone
who would be interested in this software.
Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2015-12-27 13:12:30
|
We are please to inform you the release of
The HMM-based Speech Synthesis System (HTS)
version 2.3 release December 25, 2015
for HMM-based speech synthesis. We apologize if you receive multiple
copies. Please check
http://hts.sp.nitech.ac.jp/
We would appreciate it if you would distribute this email to anyone
who would be interested in this software toolkit.
Best regards,
Keiichi Tokuda
in behalf of HTS Working Group
to...@ni...
http://www.sp.nitech.ac.jp/~tokuda/
|
|
From: <hts...@li...> - 2015-12-22 02:29:08
|
Hello all, i have got this "Error: HTS voices cannot be loaded." message when i was using the hts_voice_cmu_us_arctic_slt-1.03. $ hts_engine \ > -td tree-dur.inf -tf tree-lf0.inf -tm tree-mgc.inf \ > -md dur.pdf -mf lf0.pdf -mm mgc.pdf \ > -df lf0.win1 -df lf0.win2 -df lf0.win3 \ > -dm mgc.win1 -dm mgc.win2 -dm mgc.win3 \ > -cf gv-lf0.pdf -cm gv-mgc.pdf -ef tree-gv-lf0.inf \ > -em tree-gv-mgc.inf -k gv-switch.inf -ow output.wav \ > alice01.lab Error: HTS voices cannot be loaded. and when i was training a HTS model using the HTS-demo_NIT-ATR503-M001 , I also got this "Error: HTS voices cannot be loaded." message in my training log file. ============================================================================================= Start synthesizing waveforms using hts_engine at 2015年 12月 21日 星期一 14:18:11 CST ============================================================================================= Synthesizing a speech waveform from /home/baoalita/HTS-demo_NIT-ATR503-M001/data/labels/gen/phrase01.lab using hts_engine...Error: HTS voices cannot be loaded. what's wrong with my hts_engine? why HTS voices cannot be loaded? |
|
From: <hts...@li...> - 2015-08-26 02:25:50
|
Hi, Thank you very much for your report. The problem was fixed. Could you try CVS version? https://sourceforge.net/p/hts-engine/code/?source=navbar Regards, Keiichiro Oura 2015-08-25 17:09 GMT+09:00 <hts...@li...>: > Hi, > > [1] > If you carefully check the function and the variables, you can found the bug > below. > > > // from the initialization > HTS_Engine_set_parameter_interpolation_weight(&engine, i, 0, f); > > // sub function to set weighting > void HTS_Engine_set_parameter_interpolation_weight(HTS_Engine * engine, > size_t voice_index, size_t stream_index, double f) > { > engine->condition.parameter_iw[voice_index][stream_index] = f; > } > > BUT, in the HTS_Boolean HTS_SStreamSet_create() function, > ... > for (i = 0; i < HTS_ModelSet_get_nstream(ms); i++) { > for (j = 0, temp = 0.0; j < HTS_ModelSet_get_nvoices(ms); j++) > temp += parameter_iw[i][j]; > if (temp == 0.0) { > return FALSE; > } else if (temp != 1.0) { > for (j = 0; j < HTS_ModelSet_get_nvoices(ms); j++) > if (parameter_iw[i][j] != 0.0) > parameter_iw[i][j] /= temp; > } > ... > > Here, you can see parameter_iw[stream_index][voice_index] variable is used, > and variable i and j are mis-placed. > i.e., stream_index and voice_index should be replaced each other. > > The best way to debug this is.. change the initialization part like: > > HTS_Engine_set_parameter_interpolation_weight(&engine, 0, i, f); > > > You can debug it easily. > > > [2] > I guess, yes you can set a different interpolation weighting depends on the > stream. > > // from the initialization > HTS_Engine_set_parameter_interpolation_weight(&engine, i, 0, f); > HTS_Engine_set_parameter_interpolation_weight(&engine, i, 1, f); > > Here 0 is stream 0, 1 is stream 1. If you set different f values for the > streams, you can control the ratio like: > > HTS_Engine_set_parameter_interpolation_weight(&engine, i, 0, f1); > HTS_Engine_set_parameter_interpolation_weight(&engine, i, 1, f2); > > > Regards, > SangJin Kim > > > > On Tue, Aug 25, 2015 at 1:05 AM, <hts...@li...> > wrote: >> >> Hi All, >> >> I am trying to do some experiments with intepolation. I used the -i option >> in hts_engine, but with the parameters -i 2 10 90 I was able only to change >> the interpolation of the duration between two set of models. As can bee seen >> in the output trace file: >> >> [Global parameter] >> Sampring frequency -> 48000(Hz) >> Frame period -> 240(point) >> 5.00000(msec) >> All-pass constant -> 0.55000 >> Gamma -> 0.00000 >> Postfiltering coefficient -> 0.00000 >> Audio buffer size -> 0(sample) >> >> [Duration parameter] >> Number of states -> 5 >> Interpolation size -> 2 >> Interpolation weight[ 0] -> 10(%) >> Interpolation weight[ 1] -> 90(%) >> >> [Stream parameter] >> Stream[ 0] vector length -> 35 >> Dynamic window size -> 3 >> Interpolation size -> 2 >> Interpolation weight[ 0] -> 50(%) >> Interpolation weight[ 1] -> 50(%) >> MSD flag -> FALSE >> GV flag -> TRUE >> GV weight -> 100(%) >> GV interpolation size -> 2 >> GV interpolation weight[ 0] -> 50(%) >> GV interpolation weight[ 1] -> 50(%) >> Stream[ 1] vector length -> 1 >> Dynamic window size -> 3 >> Interpolation size -> 2 >> Interpolation weight[ 0] -> 50(%) >> Interpolation weight[ 1] -> 50(%) >> MSD flag -> TRUE >> MSD threshold -> 0.50000 >> GV flag -> TRUE >> GV weight -> 100(%) >> GV interpolation size -> 2 >> GV interpolation weight[ 0] -> 50(%) >> GV interpolation weight[ 1] -> 50(%) >> Stream[ 2] vector length -> 31 >> Dynamic window size -> 1 >> Interpolation size -> 2 >> Interpolation weight[ 0] -> 50(%) >> Interpolation weight[ 1] -> 50(%) >> MSD flag -> FALSE >> GV flag -> FALSE >> >> Is it possible to change also the interpolation ratios in streams?I mean >> Interpolation weight[ 0] and Interpolation weight[ 1]. And how is it >> possible? >> >> Thank you a lot. >> >> Best regards! >> >> Martin Sulir. >> >> >> ------------------------------------------------------------------------------ >> >> _______________________________________________ >> Hts-engine-users mailing list >> Hts...@li... >> https://lists.sourceforge.net/lists/listinfo/hts-engine-users >> > > > ------------------------------------------------------------------------------ > > _______________________________________________ > Hts-engine-users mailing list > Hts...@li... > https://lists.sourceforge.net/lists/listinfo/hts-engine-users > |
2 messages has been excluded from this view by a project administrator.
