{"id":439157,"date":"2016-11-30T05:40:03","date_gmt":"2016-11-30T05:40:03","guid":{"rendered":"https:\/\/exotel.com\/sa\/?post_type=blog&p=439157"},"modified":"2024-04-17T08:48:44","modified_gmt":"2024-04-17T08:48:44","slug":"converting-audio-wav-format-htk-format-ubuntu","status":"publish","type":"blog","link":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/","title":{"rendered":"Converting audio WAV format to HTK format on Ubuntu 14.04"},"content":{"rendered":"\n

At Exotel Labs we analyze tons of anonymized voice samples for addressing varied research problem in the voice space. While there are multiple techniques to this, a proven methodology to do voice analysis begins with converting audio into Hidden Markov Models (HMM). <\/span><\/p>\n

HTK is the Hidden Markov Model Toolkit originally developed at the Machine Intelligence Lab of the Cambridge University Engineering Department that helps in speech analyses, among a variety of applications. This blog will enumerate steps to convert a standard .wav audio file into its corresponding .htk format.
\n<\/span><\/p>\n

Though primarily stored in the WAV format, its characteristics include –<\/span><\/p>\n

— 16 kHz sampling<\/span><\/p>\n

— Monophone<\/span><\/p>\n

— 16-bit sampling<\/span><\/p>\n

— Big Endian format<\/span><\/p>\n

(Courtesy – Machine Intelligence Lab, University of Cambridge)<\/span><\/p>\n

Here is a quick primer on how to get started with HTK.<\/span><\/p>\n

1. Register and receive a password for downloading HTK software from:<\/h3>\n

    http:\/\/htk.eng.cam.ac.uk\/download.shtml<\/span><\/p>\n

2. Compile directories in the following order:<\/h3>\n

HTKLib, HLMLib, HTKTools, HLMTools as documented in the README.<\/span><\/p>\n

If compiling for CPU do a “make -f MakefileCPU all” in each directory<\/span><\/p>\n

If doing so for GPU (assuming you have Nvidia’s nvcc compiler and CUDA drivers installed), then “make -f MakefileNVCC all”<\/span><\/p>\n

3. Configuration settings and running the demo:<\/h3>\n

cd HTKDemo<\/span><\/p>\n

\/\/ Create empty directories accessed by the demo<\/span><\/em><\/p>\n

mkdir -p samples\/HTKDemo\/accs samples\/HTKDemo\/hmms samples\/HTKDemo\/hmms\/hmm.0 samples\/HTKDemo\/hmms\/hmm.1 samples\/HTKDemo\/hmms\/hmm.2 samples\/HTKDemo\/hmms\/hmm.3 samples\/HTKDemo\/proto samples\/HTKDemo\/test<\/span><\/p>\n

\/\/ Add HInit to your environment path<\/span><\/em><\/p>\n

cat \/etc\/environment<\/span><\/p>\n

…<\/p>\n

export PATH=$PATH:\/path\/to\/htk\/HTKTools<\/p>\n

\/\/Ensure the HCopy command works on your command prompt now<\/span><\/em><\/p>\n

htk# HCopy
\nUSAGE: HCopy [options] src [ + src …] tgt …
\nOption                                                            Default<\/span><\/p>\n

-a i        Use level i labels                               1
\n-e t        End copy at time t                            EOF
\n-i mlf    Save labels to mlfs                            null
\n-l dir      Output target label files to dir       current
\n-m t       Set margin of t around x\/n segs    0
\n-n i [j]    Extract i’th [to j’th] label                   off
\n-s t         Start copy at time t                           0
\n-t n        Set trace line width to n                   70
\n-x s [n]  Extract [n’th occ of] labels                off
\n-A         Print command line arguments       off
\n-C cf     Set config file to cf                              default
\n-D         Display configuration variables       off
\n-F fmt   Set source data format to fmt         as config
\n-G fmt  Set source label format to fmt         as config
\n-I mlf    Load master label file mlfs
\n-L dir    Set input label (or net) dir                 current
\n-O         Set target data format to fmt           as config
\n-P          Set target label format to fmt          as config
\n-S f        Set script file to f                                 none
\n-T N      Set trace flags to N                              0
\n-V          Print version information                  off
\n-X ext    Set input label (or net) file ext          lab<\/p>\n

\/\/ Run the demo to verify settings<\/em>
\n<\/span><\/p>\n

.\/runDemo configs\/monPlainM1S3.dcf<\/span><\/p>\n

The output should look like this –<\/span><\/p>\n

……..<\/span><\/p>\n

HResults -A -s -L labels\/bcplabs\/mon lists\/bcplist test\/te1.rec test\/te2.rec test\/te3.rec <\/span><\/p>\n

====================== HTK Results Analysis =======================<\/span><\/p>\n

 Date: Fri Nov 18 10:24:15 2016<\/span><\/p>\n

 Ref : labels\/bcplabs\/mon<\/span><\/p>\n

 Rec : test\/te1.rec<\/span><\/p>\n

 <\/span> : test\/te2.rec<\/span><\/p>\n

 <\/span> : test\/te3.rec<\/span><\/p>\n

———————— Overall Results ————————–<\/span><\/p>\n

SENT: %Correct=0.00 [H=0, S=3, N=3]<\/span><\/p>\n

WORD: %Corr=64.66, Acc=56.39 [H=86, D=36, S=11, I=11, N=133]<\/span><\/p>\n

===================================================================<\/span><\/p>\n

At this stage, the environment is well set up with all per-requisites in place.<\/span><\/p>\n

4. To define specific conversion, create a config file similar to this:<\/h3>\n

htk# cat config.code<\/span><\/p>\n

SOURCEFORMAT = WAV  — indicate the format of the input<\/span><\/p>\n

TARGETFORMAT = HTK — indicate format of output<\/span><\/p>\n

NATURALBYTEORDER = TRUE — indicate preserving byte ordering<\/span><\/p>\n

5. Generate HTK format file given an input WAV<\/h3>\n

htk# HCopy -C config.code sample_two_speakers.wav sample_two_speakers.htk<\/span><\/p>\n

htk# <\/span><\/p>\n

htk# ll sample_two_speakers*<\/span><\/p>\n

… 2658572 Nov 18 11:18 ..\/sample_two_speakers.htk<\/span><\/p>\n

… 2658604 Nov 15 13:35 ..\/sample_two_speakers.wav<\/span><\/p>\n

You will  notice that the resultant file is about 32 bytes less than the original WAV file since the HTK format strips the header.<\/span><\/p>\n

The original version of this post appeared on gogoingo<\/a>.<\/p>\n<\/body><\/html>\n","protected":false},"excerpt":{"rendered":"

At Exotel Labs we analyze tons of anonymized voice samples for addressing varied research problem in the voice space. While there are multiple techniques to this, a proven methodology to do voice analysis begins with converting audio into Hidden Markov Models (HMM). HTK is the Hidden Markov Model Toolkit originally developed at the Machine Intelligence […]<\/p>\n","protected":false},"author":18,"featured_media":439159,"template":"","meta":{"_acf_changed":false,"om_disable_all_campaigns":false},"tags":[],"blog-category":[228],"components":[],"class_list":["post-439157","blog","type-blog","status-publish","has-post-thumbnail","hentry","blog-category-technology-and-roadmap"],"acf":[],"yoast_head":"\nConverting audio WAV format to HTK format on Ubuntu 14.04 - Saudi Arabia<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Converting audio WAV format to HTK format on Ubuntu 14.04\" \/>\n<meta property=\"og:description\" content=\"At Exotel Labs we analyze tons of anonymized voice samples for addressing varied research problem in the voice space. While there are multiple techniques to this, a proven methodology to do voice analysis begins with converting audio into Hidden Markov Models (HMM). HTK is the Hidden Markov Model Toolkit originally developed at the Machine Intelligence […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/\" \/>\n<meta property=\"og:site_name\" content=\"Saudi Arabia\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-17T08:48:44+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"800\" \/>\n\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/\",\"url\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/\",\"name\":\"Converting audio WAV format to HTK format on Ubuntu 14.04 - Saudi Arabia\",\"isPartOf\":{\"@id\":\"https:\/\/exotel.com\/sa\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png\",\"datePublished\":\"2016-11-30T05:40:03+00:00\",\"dateModified\":\"2024-04-17T08:48:44+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#breadcrumb\"},\"inLanguage\":\"en-SA\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-SA\",\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage\",\"url\":\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png\",\"contentUrl\":\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png\",\"width\":800,\"height\":350},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/exotel.com\/sa\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Blogs\",\"item\":\"https:\/\/exotel.com\/sa\/en\/blog\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Converting audio WAV format to HTK format on Ubuntu 14.04\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/exotel.com\/sa\/#website\",\"url\":\"https:\/\/exotel.com\/sa\/\",\"name\":\"Saudi Arabia\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/exotel.com\/sa\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/exotel.com\/sa\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-SA\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/exotel.com\/sa\/#organization\",\"name\":\"Saudi Arabia\",\"url\":\"https:\/\/exotel.com\/sa\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-SA\",\"@id\":\"https:\/\/exotel.com\/sa\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2025\/07\/green-black-logo.png\",\"contentUrl\":\"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2025\/07\/green-black-logo.png\",\"width\":373,\"height\":110,\"caption\":\"Saudi Arabia\"},\"image\":{\"@id\":\"https:\/\/exotel.com\/sa\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Converting audio WAV format to HTK format on Ubuntu 14.04 - Saudi Arabia","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/","og_locale":"en_US","og_type":"article","og_title":"Converting audio WAV format to HTK format on Ubuntu 14.04","og_description":"At Exotel Labs we analyze tons of anonymized voice samples for addressing varied research problem in the voice space. While there are multiple techniques to this, a proven methodology to do voice analysis begins with converting audio into Hidden Markov Models (HMM). HTK is the Hidden Markov Model Toolkit originally developed at the Machine Intelligence […]","og_url":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/","og_site_name":"Saudi Arabia","article_modified_time":"2024-04-17T08:48:44+00:00","og_image":[{"width":800,"height":350,"url":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/","url":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/","name":"Converting audio WAV format to HTK format on Ubuntu 14.04 - Saudi Arabia","isPartOf":{"@id":"https:\/\/exotel.com\/sa\/#website"},"primaryImageOfPage":{"@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage"},"image":{"@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage"},"thumbnailUrl":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png","datePublished":"2016-11-30T05:40:03+00:00","dateModified":"2024-04-17T08:48:44+00:00","breadcrumb":{"@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#breadcrumb"},"inLanguage":"en-SA","potentialAction":[{"@type":"ReadAction","target":["https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/"]}]},{"@type":"ImageObject","inLanguage":"en-SA","@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#primaryimage","url":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png","contentUrl":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2023\/06\/sound-1781569_1280-800x350-1.png","width":800,"height":350},{"@type":"BreadcrumbList","@id":"https:\/\/exotel.com\/sa\/en\/blog\/converting-audio-wav-format-htk-format-ubuntu\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/exotel.com\/sa\/en\/"},{"@type":"ListItem","position":2,"name":"Blogs","item":"https:\/\/exotel.com\/sa\/en\/blog\/"},{"@type":"ListItem","position":3,"name":"Converting audio WAV format to HTK format on Ubuntu 14.04"}]},{"@type":"WebSite","@id":"https:\/\/exotel.com\/sa\/#website","url":"https:\/\/exotel.com\/sa\/","name":"Saudi Arabia","description":"","publisher":{"@id":"https:\/\/exotel.com\/sa\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/exotel.com\/sa\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-SA"},{"@type":"Organization","@id":"https:\/\/exotel.com\/sa\/#organization","name":"Saudi Arabia","url":"https:\/\/exotel.com\/sa\/","logo":{"@type":"ImageObject","inLanguage":"en-SA","@id":"https:\/\/exotel.com\/sa\/#\/schema\/logo\/image\/","url":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2025\/07\/green-black-logo.png","contentUrl":"https:\/\/exotel.com\/sa\/wp-content\/uploads\/sites\/8\/2025\/07\/green-black-logo.png","width":373,"height":110,"caption":"Saudi Arabia"},"image":{"@id":"https:\/\/exotel.com\/sa\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/blog\/439157","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/types\/blog"}],"author":[{"embeddable":true,"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/users\/18"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/media\/439159"}],"wp:attachment":[{"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/media?parent=439157"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/tags?post=439157"},{"taxonomy":"blog-category","embeddable":true,"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/blog-category?post=439157"},{"taxonomy":"components","embeddable":true,"href":"https:\/\/exotel.com\/sa\/en\/wp-json\/wp\/v2\/components?post=439157"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}