Questions tagged [htk]

HTK - HMM Tool Kit A set of tools for training, testing and deploying Hidden Markov Models for statistical machine learning tasks, such as Speaker Verification and Recognition

The HTK (HMM Tool Kit) has been developed by the University of Cambridge. It contains a set of tools for training, testing (building) and eventual deployment of Hidden Markov Models (HMMs) primarily for speech recognition tasks. Its use, however, can be and has been extended to any machine learning/pattern recognition task.

The HTK website can be found by clicking on this sentence.

91 questions
86
votes
2 answers

"fatal error: bits/libc-header-start.h: No such file or directory" while compiling HTK

I'm getting the following issue when trying to run make on the HTK library: (cd HTKLib && make HTKLib.a) \ || case "" in *k*) fail=yes;; *) exit 1;; esac; make[1]: Entering directory '/home/william/speech/htk/HTK-3.4.1/htk/HTKLib' gcc -m32 -ansi…
William
  • 1,154
  • 1
  • 9
  • 15
4
votes
1 answer

Can't install HTK on linux

I wan't to use ALIZE for speaker recognition and after the instalation there is one of the steps: feature extraction using SPRO or HTK So I downloaded zip file of HTK and using terminal I configured everything, but when entering make all I'm getting…
Nikas Žalias
  • 1,594
  • 1
  • 23
  • 51
3
votes
1 answer

read HTK binary file in matlab

I run HTK package to extract MFCC features from my data. But now this features are stored in .mfc file format which is according to the htk book, big endian binary file. When I open these files in matlab there is some values which seems to be header…
MMD
  • 33
  • 4
3
votes
2 answers

Building Jarvis like application for local languages

The jarvis application that is currently developed, is in English. I want to customize it to use local language. How to develop this kind of app for local languages? what kind of programming languages I must know to proceed to the development? I…
senye
  • 175
  • 2
  • 15
3
votes
1 answer

How to Install HTK on Android?

Similar to this question. Since I don't want to pass the voice data to a server, doing this may cost me more time. I wonder if I can use HTK to recognize the voice data locally with the Android application so that I won't need to pass that audio to…
user978112
  • 151
  • 1
  • 6
3
votes
1 answer

HTK: HVite can't find hmm

I want to build a speech recognition system using HTK and therefore downloaded a pre-trained acoustic model with tied states from http://www.keithv.com/software/htk/us/ (Training data: WSJ SI-84). However, when I try to run HVite with my…
Dominik
  • 55
  • 1
  • 6
2
votes
3 answers

HTK HEREST ISSUE

I'm doing some speech recognition using HTK (HMM ToolKit) and I'm getting this odd error: ERROR [+7390] StepAlpha: Alpha prune failed sq(16) > qHi(15) I have tried to play around with pruning but only those 15/16 would change to other numbers, I…
Tim
  • 41
  • 4
2
votes
1 answer

How to read the .mfc file which is created by HTK in python environment

I have some file which are created by HTK file, ended by .mfc. I want to read the file into python3, Is there any solution? Thanks
Yanpei
  • 31
  • 1
  • 4
2
votes
1 answer

HTK - What do MFCCs of an HMM model and Input WAV File represent?

While creating MFCCs following Voxforge's tutorial for a Speech to Text System using HTK (Hidden Markov Model Tool Kit), we are required to define a prototype model for our phones. I am trying to wrap my head around this this file. ~o 25…
Ajay H
  • 794
  • 2
  • 11
  • 28
2
votes
1 answer

Converting HTK model to Pocketsphinx

I have a working model built with HTK for online handwriting recognition. Now I want to build another recognition system for Android. After some research I found out that PocketSphinx has a version running on Android OS. Now, what I think of is to…
2
votes
1 answer

How about the speed of scikit-learn HMM compared with HTK?

I'm doing scene text recognition with HMM. I'm doubt of the speed of scikit-learn HMM code for training and predicting compared with HTK, for sklearn HMM is written in Python. My data is really huge (tens of gigabytes), so speed is a critical…
nn0p
  • 1,189
  • 12
  • 28
2
votes
1 answer

Open source tools for recognizing untranscribed speech without a dictionary

Just doing some general research. Are there any open source (or even paid?) tools / programs that do the following: INPUT: an audio file of some unlabeled speech, maybe a few sentences long, (no indication as to what the phonetic transcriptions are…
kearly
  • 67
  • 7
2
votes
0 answers

Python Audio Aligner

I need some help with a python script. It is the Penn Phonetics Audio Aligner. I got it installed and everything is working, just a little too well :) I am trying to match up a transcript with the time in the audio it is spoken, which this does, but…
Alan
  • 2,046
  • 2
  • 20
  • 43
2
votes
2 answers

Toolkits to design a TTS (Text-to-speech) system for a custom language?

I'd like to create a TTS system for a native american language (wayuunaiki). The language is written in latin (western) alphabet. I also have information about the phonetics (the rules to convert each word into IPA symbols). I'm planning to create a…
2
votes
1 answer

Decode a ulaw encoded SPH file

This problem is solved My task: I have a .sph file with the following file-header: NIST_1A 1024 conversation_id -s4 2001 database_id -s25 Switchboard-1_release-2.0 channel_count -i 1 sample_coding -s4 ulaw channels_interleaved -s4 TRUE …
sflee
  • 1,659
  • 5
  • 32
  • 63
1
2 3 4 5 6 7