Acoustic Model Discussions

Search

Subject User Views Replies Rating Date Last Reply
*READ THIS FIRST* for questions about Acoustic Model Training kmaclean 7042 4 11 12/4/2010 @ 10:54 am *READ THIS FIRST* for questions about Acoustic Model Training by kmaclean on 12/4/2010 @ 10:54 am
Training recommendation? Tom J. 4646 9 0 11/9/2020 @ 11:14 am Re: Training recommendation? by Marie on 5/20/2022 @ 11:24 pm
Questions about the Nightly Builds odfi 3334 1 0 7/22/2020 @ 11:16 am Re: Questions about the Nightly Builds by kmaclean on 7/24/2020 @ 9:58 am
HMM Def Error: Mean Vector expected at line 6/col 66/char 117 in hmm0/hmmdefs ... Jikkan 3303 2 1 6/22/2020 @ 10:33 am Re: HMM Def Error: Mean Vector expected at line 6/col 66/char 117 in hmm0/hmmdefs ... by kmaclean on 6/25/2020 @ 10:30 am
ERROR [+1113] : writing a numpy array into HTK readable format shareefbabu 3596 2 0 11/29/2019 @ 1:02 am Re: ERROR [+1113] : writing a numpy array into HTK readable format by Rold1940 on 2/9/2020 @ 5:46 am
Force Alignment & Phone decoder Anita 4599 1 1 1/31/2016 @ 1:41 pm Re: Force Alignment & Phone decoder by wenjiep on 1/19/2020 @ 9:51 pm
New English Zamia-Speech Models released guenter 7763 5 6 6/23/2018 @ 5:38 pm Re: New English Zamia-Speech Models released by guenter on 6/20/2019 @ 3:36 am
Humans are great, but why not use commercial (and OSS) text to speech engines too? trevarthan 11979 4 108 3/31/2007 @ 2:11 am Re: Humans are great, but why not use commercial (and OSS) text to speech engines too? by kmaclean on 5/27/2019 @ 5:42 pm
Children English Acoustic Model dimas09 4261 1 0 4/9/2019 @ 10:27 am Re: Children English Acoustic Model by kmaclean on 4/9/2019 @ 11:53 am
Looking for Sphinx4 8kHz Model for German, Spanish and French Pacer 4733 1 0 6/29/2016 @ 6:29 am Re: Looking for Sphinx4 8kHz Model for German, Spanish and French by fabriciofah9 on 6/22/2018 @ 10:39 pm
New 160k words 1080 hours english models released guenter 6838 4 2 10/30/2017 @ 5:01 pm Re: New 160k words 1080 hours english models released by guenter on 5/8/2018 @ 2:17 pm
ERROR [+5010] InitSource: Cannot open source file beg-w_end manusha 2583 0 0 4/3/2018 @ 2:18 am ERROR [+5010] InitSource: Cannot open source file beg-w_end by manusha on 4/3/2018 @ 2:18 am
I know, how to get data for training jflsbtovs64mduyg4ngt 5393 2 6 11/13/2014 @ 4:00 pm Re: I know, how to get data for training by Andrew767 on 3/17/2018 @ 9:59 pm
How to detect ringback tone, ivrs tone and hold music in an audio recording containing conversation between two people stansilasmiles 4795 1 0 12/4/2017 @ 10:25 pm Re: How to detect ringback tone, ivrs tone and hold music in an audio recording containing conversation between two people by kmaclean on 12/5/2017 @ 8:25 am
HTK DNN add layer issue kothemel 2718 0 0 8/24/2017 @ 10:42 am HTK DNN add layer issue by kothemel on 8/24/2017 @ 10:42 am
Combine acoustic model with language model and detect silence between words Head7 5702 3 2 4/4/2017 @ 5:46 am Re: Combine acoustic model with language model and detect silence between words by Praiseworthy on 4/11/2017 @ 8:47 am
ERROR [+2219] HRest: source HMM file name expected aniewiadomy 5746 1 0 3/28/2017 @ 6:04 am Re: ERROR [+2219] HRest: source HMM file name expected by Praiseworthy on 4/10/2017 @ 11:15 am
Error [+6510] Ruagal 5045 3 17 3/26/2014 @ 11:37 pm Re: Error [+6510] by Visitor on 4/8/2017 @ 1:14 am
What about MFCC output? chawin 5133 1 0 10/7/2015 @ 1:55 am Re: What about MFCC output? by Head7 on 4/5/2017 @ 3:37 am
adaptation mllr in htk 3.4 maituan2012 4998 2 1 3/21/2017 @ 5:07 am Re: adaptation mllr in htk 3.4 by Praiseworthy on 3/25/2017 @ 7:34 am
How to Adapt Acoustic Model using HTK-3.4.1 ? Babaloo 4656 1 0 3/8/2017 @ 1:49 pm Re: How to Adapt Acoustic Model using HTK-3.4.1 ? by Praiseworthy on 3/25/2017 @ 7:15 am
Forced alignment diwakarg 2754 0 0 12/13/2016 @ 6:34 pm Forced alignment by diwakarg on 12/13/2016 @ 6:34 pm
NullPointerException when load n-gram language model Pacer 3035 0 0 7/22/2016 @ 8:59 am NullPointerException when load n-gram language model by Pacer on 7/22/2016 @ 8:59 am
Pruning-On[250.0 150.0 1000.0] ERROR [+7321] CreateInsts: Unknown label vbk anketvit 2463 0 1 7/21/2016 @ 5:27 am Pruning-On[250.0 150.0 1000.0] ERROR [+7321] CreateInsts: Unknown label vbk by anketvit on 7/21/2016 @ 5:27 am
how to make tree1.hed for another language Masoud 5230 1 0 5/30/2016 @ 9:02 am Re: how to make tree1.hed for another language by kmaclean on 5/30/2016 @ 9:30 am
English Gigaword language model training recipe JohnTitor 7447 9 2 4/20/2016 @ 9:55 am Re: English Gigaword language model training recipe by wildcard on 5/17/2016 @ 5:15 am
Speech feature definition Noah 4811 2 6 10/31/2011 @ 11:35 pm Re: Speech feature definition by [email protected] on 2/28/2016 @ 2:37 pm
universal accoustic/language models? + some other questions ardwennem2 6617 3 1 12/16/2015 @ 6:58 am Re: universal accoustic/language models? + some other questions by colbec on 1/12/2016 @ 4:46 am
setp 2: error in use dictionnary BEEP in the place of dictionary "voxforge_lexicon" imene 14926 13 118 7/21/2008 @ 1:20 pm Re: How to use Beep pronunciation dictionary with HTK by Arthi on 11/30/2015 @ 11:35 pm
ERROR [+15190] AddWordToMap:Word map is full liang_cckybg 4656 1 3 3/25/2013 @ 3:51 am Re: ERROR [+15190] AddWordToMap:Word map is full by Visitor on 10/22/2015 @ 2:14 am