{"id":17919,"date":"2015-01-01T21:24:04","date_gmt":"2015-01-02T02:24:04","guid":{"rendered":"https:\/\/reactivemusic.net\/?p=17919"},"modified":"2015-01-15T18:15:51","modified_gmt":"2015-01-15T23:15:51","slug":"hearing-voices","status":"publish","type":"post","link":"https:\/\/reactivemusic.net\/?p=17919","title":{"rendered":"Hearing voices"},"content":{"rendered":"<p><span style=\"font-style: italic; color: #333333;\">A presentation for Berklee BTOT 2015\u00a0<\/span><a style=\"font-style: italic;\" href=\"http:\/\/www.berklee.edu\/faculty\">http:\/\/www.berklee.edu\/faculty<\/a><\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-18065\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png\" alt=\"\" width=\"300\" height=\"95\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-1024x324.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM.png 1622w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>(<cite>KITT dashboard by Dave Metlesits<\/cite>)<\/p>\n<p class=\"lead\">The voice was the first musical instrument. Humans are not the only source of musical voices. Machines have voices. Animals too.<\/p>\n<h5>Topics<\/h5>\n<ul>\n<li>synthesizing voices (formant synthesis, text to speech, Vocaloid)<\/li>\n<li>processing voices (pitch-shifting, time-stretching, vocoding, filtering, harmonizing),<\/li>\n<li>voices of the natural world<\/li>\n<li>fictional languages and animals<\/li>\n<li>accents<\/li>\n<li>speech and music recognition<\/li>\n<li>processing voices as pictures<\/li>\n<li>removing music from speech<\/li>\n<li>removing voices<\/li>\n<\/ul>\n<h4>Voices<\/h4>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-10266\" title=\"Screen Shot 2014-03-24 at 10.52.51 PM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/03\/Screen-Shot-2014-03-24-at-10.52.51-PM-300x53.png\" alt=\"\" width=\"300\" height=\"53\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/03\/Screen-Shot-2014-03-24-at-10.52.51-PM-300x53.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/03\/Screen-Shot-2014-03-24-at-10.52.51-PM.png 600w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/p>\n<p>We instantly recognize people and animals by their voices. As an artist we work to develop our own voice.\u00a0Voices contain\u00a0information beyond words. Think of R2D2 or Chewbacca.<\/p>\n<p>There is also information <em>between<\/em> words: &#8220;Palin Biden Silences&#8221; David Tinapple, 2008:\u00a0<a href=\"http:\/\/vimeo.com\/38876967\">http:\/\/vimeo.com\/38876967<\/a><\/p>\n<h4>Synthesizing voices<\/h4>\n<h5>The vocal spectrum<\/h5>\n<p>What&#8217;s in a voice?<\/p>\n<p><a style=\"color: #2795b6;\" href=\"http:\/\/sounddesignwithmax.blogspot.com\/2013\/05\/i.html\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-9299\" title=\"Screen Shot 2014-01-09 at 2.49.30 AM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/01\/Screen-Shot-2014-01-09-at-2.49.30-AM-300x277.png\" alt=\"\" width=\"300\" height=\"277\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/01\/Screen-Shot-2014-01-09-at-2.49.30-AM-300x277.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/01\/Screen-Shot-2014-01-09-at-2.49.30-AM-324x300.png 324w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/01\/Screen-Shot-2014-01-09-at-2.49.30-AM.png 697w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<ul>\n<li><span style=\"line-height: 1.6;\">Formant synthesis in Max by\u00a0<\/span>Mark Durham:\u00a0<a style=\"line-height: normal;\" href=\"https:\/\/reactivemusic.net\/?p=9294\">https:\/\/reactivemusic.net\/?p=9294<\/a>\u00a0(singing vowels with formants)<\/li>\n<li>Formant synthesis Tutorial by Jordan Smith:\u00a0<a style=\"line-height: normal;\" href=\"https:\/\/reactivemusic.net\/?p=9290\">https:\/\/reactivemusic.net\/?p=9290<\/a>\u00a0(making consonants with noise)<\/li>\n<\/ul>\n<h6>Singing chords<\/h6>\n<p>Humans acting like synthesizers.<\/p>\n<ul>\n<li>Singing chords: Lalah Hathaway\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=c5AdOZtRdfE\">https:\/\/www.youtube.com\/watch?v=c5AdOZtRdfE<\/a>\u00a0(0:30)<\/li>\n<li>Tuvan throat singing:\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=5wHbIWH_NGc\">https:\/\/www.youtube.com\/watch?v=5wHbIWH_NGc<\/a>\u00a0(near the end of the video)<\/li>\n<li>Polyphonic overtone singing: Anna-Maria Hefele\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=vC9Qh709gas\">https:\/\/www.youtube.com\/watch?v=vC9Qh709gas<\/a><\/li>\n<\/ul>\n<h6>More about formants<\/h6>\n<ul>\n<li>Formants (Wikipedia)\u00a0<a href=\"http:\/\/en.wikipedia.org\/wiki\/Formant\">http:\/\/en.wikipedia.org\/wiki\/Formant<\/a><\/li>\n<li>Rooms have resonances: &#8220;<a href=\"http:\/\/en.wikipedia.org\/wiki\/I_Am_Sitting_in_a_Room\">I am sitting in a Room<\/a>&#8221; by Alvin Lucier<\/li>\n<li>Singer&#8217;s formant (2800-3400Hz).<\/li>\n<\/ul>\n<h5><span style=\"color: #222222; font-family: 'Helvetica Neue', Helvetica, Helvetica, Arial, sans-serif; font-size: 17px; line-height: 1.1;\">Text to speech<\/span><\/h5>\n<p>Teaching machines to talk.<\/p>\n<p><a style=\"color: #2795b6;\" href=\"http:\/\/www.paia.com\/ProdArticles\/vocodwrk.htm\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-17219\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/10\/vocodblk.gif-300x132.png\" alt=\"vocodblk.gif\" width=\"300\" height=\"132\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/10\/vocodblk.gif-300x132.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/10\/vocodblk.gif.png 590w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<ul>\n<li>phonemes (unit of sound)<\/li>\n<li>diphones (combination of phonemes) (Mac OS &#8220;Macintalk 3 \u00a0pro&#8221;)<\/li>\n<li>morphemes (unit of meaning)<\/li>\n<li>prosody (musical quality of speech)<\/li>\n<\/ul>\n<h6>Methods<\/h6>\n<ul>\n<li>articulatory (anatomical model)<\/li>\n<li>formant (additive synthesis) (speak and spell)<\/li>\n<li>concatentative (building blocks) (Mac Os)<\/li>\n<\/ul>\n<p>Try the &#8216;say&#8217; command (in Mac OS terminal), for example: say hello<\/p>\n<h6>More about text to speech<\/h6>\n<ul>\n<li>History of speech synthesis\u00a0<a style=\"line-height: normal;\" href=\"http:\/\/research.spa.aalto.fi\/publications\/theses\/lemmetty_mst\/chap5.html\">http:\/\/research.spa.aalto.fi\/publications\/theses\/lemmetty_mst\/chap5.html<\/a>\u00a0(Helsinki University of Technology 1999)<\/li>\n<li>Speech synthesizers, 2014\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=18141\">https:\/\/reactivemusic.net\/?p=18141<\/a><\/li>\n<li>Speech synthesis web API\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=18138\">https:\/\/reactivemusic.net\/?p=18138<\/a><\/li>\n<\/ul>\n<h5>Vocoders<\/h5>\n<p>Combining the energy of voice with musical instruments (convolution)<\/p>\n<ul>\n<li>Peter Frampton &#8220;talkbox&#8221;:\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=EqYDQPN_nXQ\">https:\/\/www.youtube.com\/watch?v=EqYDQPN_nXQ<\/a>\u00a0(about 5:42) &#8211; Where is the exciting audience noise in this video?<\/li>\n<li>Ableton Live example: Local file:\u00a0Max\/MSP: examples\/effects\/classic-vocoder-folder\/classic_vocoder.maxpat<\/li>\n<li>Max vocoder tutorial (In the frequency domain), by dude837 &#8211; Sam Tarakajian\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=17362\">https:\/\/reactivemusic.net\/?p=17362<\/a>\u00a0(local file: dude837\/4-vocoder\/robot-master.maxpat<\/li>\n<\/ul>\n<h6>More about vocoders<\/h6>\n<ul>\n<li>How vocoders work, by Craig Anderton:\u00a0<a style=\"line-height: normal;\" href=\"https:\/\/reactivemusic.net\/?p=17218\">https:\/\/reactivemusic.net\/?p=17218<\/a><\/li>\n<li>Wikipedia:\u00a0<a style=\"line-height: normal;\" href=\"http:\/\/en.wikipedia.org\/wiki\/Vocoder\">http:\/\/en.wikipedia.org\/wiki\/Vocoder<\/a>. Engineers conserving information to reduce bandwith<\/li>\n<li>Heterodyne filter:\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=17338\">https:\/\/reactivemusic.net\/?p=17338<\/a>\u00a0&#8211; digital emulation of an analog filter bank.<\/li>\n<li>Max\/MSP: examples\/effects\/classic-vocoder-folder\/classic_vocoder.maxpat<\/li>\n<\/ul>\n<h5>Vocaloid<\/h5>\n<p>By Yamaha<\/p>\n<p><a style=\"color: #2795b6;\" href=\"http:\/\/en.wikipedia.org\/wiki\/Hatsune_Miku\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-14928\" title=\"Screen Shot 2014-06-17 at 3.13.32 PM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/09\/Screen-Shot-2014-06-17-at-3.13.32-PM-300x219.png\" alt=\"\" width=\"300\" height=\"219\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/09\/Screen-Shot-2014-06-17-at-3.13.32-PM-300x219.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/09\/Screen-Shot-2014-06-17-at-3.13.32-PM.png 387w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>(text + notation = singing)<\/p>\n<ul>\n<li>Vocaloid website:\u00a0<a style=\"line-height: normal;\" href=\"http:\/\/www.vocaloid.com\/en\/\">http:\/\/www.vocaloid.com\/en\/<\/a><\/li>\n<li>Hatsune Miku:\u00a0<a style=\"line-height: normal;\" href=\"https:\/\/reactivemusic.net\/?p=6891\">https:\/\/reactivemusic.net\/?p=6891<\/a><\/li>\n<\/ul>\n<p>Demo tracks:\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=QWkHypp3kuQ\">https:\/\/www.youtube.com\/watch?v=QWkHypp3kuQ<\/a><\/p>\n<ul>\n<li>Vocaloid tutorial\n<ul>\n<li>#1\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=vcJDTDBWTrw\">https:\/\/www.youtube.com\/watch?v=vcJDTDBWTrw<\/a>\u00a0(entering notes and lyrics &#8211; 1:25)<\/li>\n<li>#2\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=qpGwgIyMGOk\">https:\/\/www.youtube.com\/watch?v=qpGwgIyMGOk<\/a>\u00a0(raw sound &#8211; 0:42)<\/li>\n<li>#5\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=YEAuL6Q2j-0\">https:\/\/www.youtube.com\/watch?v=YEAuL6Q2j-0<\/a>\u00a0(with phrasing, vibrato, etc.,- 1:00)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Vocaloop device\u00a0<a href=\"http:\/\/vocaloop.jp\/\">http:\/\/vocaloop.jp\/<\/a>\u00a0demo:\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=xLpX2M7I6og#t=24\">https:\/\/www.youtube.com\/watch?v=xLpX2M7I6og#t=24<\/a><\/p>\n<h4>Processing voices<\/h4>\n<p>Transformation<\/p>\n<p>Pitch transposing a baby\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=2458\">https:\/\/reactivemusic.net\/?p=2458<\/a><\/p>\n<h5>Real time pitch shifting<\/h5>\n<p>Autotune: &#8220;T-Pain effect&#8221; ,(I-am-T-Pain bySmule), &#8220;Lollipop&#8221; by Lil&#8217; Wayne. &#8220;Woods&#8221; by Bon Iver\u00a0<a href=\"https:\/\/www.youtube.com\/watch?v=1_cePGP6lbU\">https:\/\/www.youtube.com\/watch?v=1_cePGP6lbU<\/a><\/p>\n<h6>Autotuna in Max 7<\/h6>\n<p><cite>by Matthew Davidson<\/cite><\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-12.39.16-PM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-18039\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-12.39.16-PM-300x172.png\" alt=\"\" width=\"300\" height=\"172\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-12.39.16-PM-300x172.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-12.39.16-PM-1024x590.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-12.39.16-PM.png 1738w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>Local file: max-teaching-examples\/autotuna-test.maxpat<\/p>\n<h6>InstantDecomposer in Pure Data (Pd)<\/h6>\n<p><cite>by Katja Vetter<\/cite><\/p>\n<p><a href=\"http:\/\/www.katjaas.nl\/slicejockey\/slicejockey.html\">http:\/\/www.katjaas.nl\/slicejockey\/slicejockey.html<\/a><\/p>\n<p>Autocorrelation: (helmholtz~ Pd external)\u00a0\u201cHelmholtz finds the pitch\u201d\u00a0<a href=\"http:\/\/www.katjaas.nl\/helmholtz\/helmholtz.html\">http:\/\/www.katjaas.nl\/helmholtz\/helmholtz.html<\/a><\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-10-at-1.14.05-AM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-18099\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-10-at-1.14.05-AM-300x167.png\" alt=\"\" width=\"300\" height=\"167\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-10-at-1.14.05-AM-300x167.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-10-at-1.14.05-AM-1024x573.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-10-at-1.14.05-AM.png 1190w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>(^^ is input pitch, preset #9 is normal)<\/p>\n<ul>\n<li>local file: InstantDecomposer version: tkzic\/pdweekend2014\/IDecTouch\/IDecTouch.pd<\/li>\n<li>local file: slicejockey2test2\/slicejockey2test2.pd<\/li>\n<\/ul>\n<h5>Phasors and Granular synthesis<\/h5>\n<p>Disassembling time into very small pieces<\/p>\n<ul>\n<li>sorting noise; <a style=\"line-height: normal;\" href=\"(helmholtz~%20external)\u00a0\u201cHelmholtz finds the pitch\u201d\u00a0http:\/\/www.katjaas.nl\/helmholtz\/helmholtz.html\">http:\/\/youtu.be\/kPRA0W1kECg<\/a><\/li>\n<li>Phasors:\u00a0<a style=\"line-height: normal;\" href=\"https:\/\/reactivemusic.net\/?p=17353\">https:\/\/reactivemusic.net\/?p=17353<\/a><\/li>\n<\/ul>\n<h6>Time-stretching<\/h6>\n<p><cite>Adapted from Andy Farnell, &#8220;Designing Sound&#8221;<\/cite><\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/?p=11385\">https:\/\/reactivemusic.net\/?p=11385<\/a>\u00a0Download these patches from:\u00a0<a href=\"https:\/\/github.com\/tkzic\/max-projects\">https:\/\/github.com\/tkzic\/max-projects<\/a>\u00a0folder: granular-timestretch<\/p>\n<ul>\n<li>Basic granular synthesis: graintest3.maxpat<\/li>\n<li>Time-stretching: timestretch5.maxpat<\/li>\n<\/ul>\n<p><a style=\"color: #2795b6;\" href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/05\/Screen-Shot-2014-05-16-at-6.37.20-PM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-11386\" title=\"Screen Shot 2014-05-16 at 6.37.20 PM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/05\/Screen-Shot-2014-05-16-at-6.37.20-PM-300x188.png\" alt=\"\" width=\"300\" height=\"188\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/05\/Screen-Shot-2014-05-16-at-6.37.20-PM-300x188.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/05\/Screen-Shot-2014-05-16-at-6.37.20-PM-1024x643.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/05\/Screen-Shot-2014-05-16-at-6.37.20-PM.png 1606w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<h6>More about phasors and granular synthesis<\/h6>\n<ul>\n<li>Shepard tone upward glissando by Chris Dobrian:\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=17255\">https:\/\/reactivemusic.net\/?p=17255<\/a><\/li>\n<li>\u201cFalling Falling\u201d (Visual Shepard tone)\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=17251\">https:\/\/reactivemusic.net\/?p=17251<\/a><\/li>\n<li>Ableton Live &#8211; granulator (Robert Henke)<\/li>\n<\/ul>\n<h5>Phase vocoder<\/h5>\n<p>&#8230;coming soon<\/p>\n<h5 style=\"color: #333333;\">Sonographic sound processing<\/h5>\n<p>Changing sound into pictures and back into sound<\/p>\n<p style=\"color: #333333;\"><cite>by\u00a0Tadej Droljc<\/cite><\/p>\n<p style=\"color: #333333;\"><cite>\u00a0<\/cite><a style=\"font-style: inherit; color: #1b8be0;\" href=\"https:\/\/reactivemusic.net\/?p=16887\">https:\/\/reactivemusic.net\/?p=16887<\/a><\/p>\n<p><iframe loading=\"lazy\" title=\"Sonographic Sound Processing in Max\/MSP and Jitter\" width=\"525\" height=\"394\" src=\"https:\/\/www.youtube.com\/embed\/0PrIO5tweeo?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<p>(Example of 3d speech processing at 4:12)<\/p>\n<p>local file: SSP-dissertation\/4 &#8211; Max\/MSP\/Jitter Patch of PV With Spectrogram as a Spectral Data Storage and User Interface\/basic_patch.maxpat<\/p>\n<p>Try recording a short passage, then set bound mode to 4, and click autorotate<\/p>\n<h4>Speech to text<\/h4>\n<p>Understanding the meaning of speech<\/p>\n<h5>The Google Speech API<\/h5>\n<p>A conversation with a robot in Max<\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/?p=9834\">https:\/\/reactivemusic.net\/?p=9834<\/a><\/p>\n<p><a style=\"line-height: 1.6;\" href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/02\/Screen-Shot-2014-02-11-at-4.35.19-PM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-9835\" title=\"Screen Shot 2014-02-11 at 4.35.19 PM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/02\/Screen-Shot-2014-02-11-at-4.35.19-PM-300x184.png\" alt=\"\" width=\"300\" height=\"184\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/02\/Screen-Shot-2014-02-11-at-4.35.19-PM-300x184.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/02\/Screen-Shot-2014-02-11-at-4.35.19-PM-1024x629.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2014\/02\/Screen-Shot-2014-02-11-at-4.35.19-PM.png 1050w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>Google speech uses neural networks, statistics, and large quantities of data.<\/p>\n<h6>More about speech to text<\/h6>\n<ul>\n<li>Real time German\/English translator (Microsoft) \u00a0<a href=\"http:\/\/digg.com\/video\/heres-microsoft-demoing-their-breakthrough-in-real-time-translated-conversation\">http:\/\/digg.com\/video\/heres-microsoft-demoing-their-breakthrough-in-real-time-translated-conversation<\/a><\/li>\n<li>Skype translator &#8211; Spanish\/English:\u00a0<a href=\"http:\/\/www.skype.com\/en\/translator-preview\/\">http:\/\/www.skype.com\/en\/translator-preview\/<\/a><\/li>\n<li>Dragon Naturally Speaking (Nuance) accidentally converts music to poetry<\/li>\n<li><\/li>\n<\/ul>\n<h4>Voices of the natural world<\/h4>\n<p>Changes in the environment reflected by sound<\/p>\n<ul>\n<li>Bernie Krause: &#8220;Soundscapes&#8221;\n<ul>\n<li>The Voice of The Natural World:\u00a0<a href=\"http:\/\/blog.ted.com\/2013\/06\/12\/the-voice-of-the-natural-world-bernie-krause-at-tedglobal-2013\/\">http:\/\/blog.ted.com\/2013\/06\/12\/the-voice-of-the-natural-world-bernie-krause-at-tedglobal-2013\/<\/a><\/li>\n<li>TED:\u00a0<a href=\"http:\/\/www.ted.com\/talks\/bernie_krause_the_voice_of_the_natural_world\">http:\/\/www.ted.com\/talks\/bernie_krause_the_voice_of_the_natural_world<\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4>Fictional languages and animals<\/h4>\n<p>&#8220;You can talk to the animals&#8230;&#8221;<\/p>\n<ul>\n<li>Derek Abbot&#8217;s animal noise page:\u00a0<a href=\"http:\/\/www.eleceng.adelaide.edu.au\/Personal\/dabbott\/animal.html\">http:\/\/www.eleceng.adelaide.edu.au\/Personal\/dabbott\/animal.html<\/a><\/li>\n<li>Quack project \u00a0<a href=\"http:\/\/www.quack-project.com\/table.cgi\">http:\/\/www.quack-project.com\/table.cgi<\/a><\/li>\n<li>Fictional language dialog by Naila Burney:\u00a0\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=7242\">https:\/\/reactivemusic.net\/?p=7242<\/a><\/li>\n<\/ul>\n<p>Pig creatures example:\u00a0<a href=\"http:\/\/vimeo.com\/64543087\">http:\/\/vimeo.com\/64543087<\/a><\/p>\n<ul>\n<li>0:00 Neutral<\/li>\n<li>0:32 Single morphemes &#8211; neutral mode<\/li>\n<li>0:37 Series, with unifying sounds and breaths<\/li>\n<li>1:02 Neutral, layered<\/li>\n<li>1:12 Sad<\/li>\n<li>1:26 Angry<\/li>\n<li>1:44 More Angry<\/li>\n<li>2:11 Happy<\/li>\n<\/ul>\n<p>What about Jar Jar Binks?<\/p>\n<h4>Accents<\/h4>\n<p>The sound changes but the words remain the same.<\/p>\n<p>The Speech accent archive\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=9436\">https:\/\/reactivemusic.net\/?p=9436<\/a><\/p>\n<h4>Finding and removing music in speech<\/h4>\n<p>We are always singing.<\/p>\n<h5>Jamming with speech<\/h5>\n<ul>\n<li>Drummer jams with a speed-talking auctioneer:\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=7140\">https:\/\/reactivemusic.net\/?p=7140<\/a><\/li>\n<li><span style=\"color: #333333;\">Guitarist imitates crying\u00a0<\/span><span style=\"color: #333333;\">politician:\u00a0<\/span><a style=\"font-style: inherit; color: #1b8be0;\" href=\"http:\/\/digg.com\/video\/guitarist-plays-along-to-sobbing-japanese-politician\">http:\/\/digg.com\/video\/guitarist-plays-along-to-sobbing-japanese-politician<\/a><\/li>\n<\/ul>\n<h5>Removing music from speech<\/h5>\n<h6>SMS-tools<\/h6>\n<p><cite>by Xavier Serra and UPF<\/cite><\/p>\n<p>Harmonic Model Plus Residual (HPR) &#8211; Build a spectrogram using STFT, then identify where there is strong correlation to a tonal harmonic structure (music). This is the harmonic model of the sound. Subtract it from the original spectrogram to get the residual (noise).<\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.37-AM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-17994\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.37-AM-300x194.png\" alt=\"Screen Shot 2015-01-06 at 1.40.37 AM\" width=\"300\" height=\"194\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.37-AM-300x194.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.37-AM-1024x664.png 1024w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.37-AM.png 1938w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.12-AM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-17995\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.12-AM-169x300.png\" alt=\"Screen Shot 2015-01-06 at 1.40.12 AM\" width=\"169\" height=\"300\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.12-AM-169x300.png 169w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.12-AM-578x1024.png 578w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-06-at-1.40.12-AM.png 710w\" sizes=\"auto, (max-width: 169px) 100vw, 169px\" \/><\/a><\/p>\n<p>Settings for above example:<\/p>\n<ul>\n<li>Window size: 1800 (SR \/ f0 * lobeWidth) 44100 \/ 200 * 8 = 1764<\/li>\n<li>FFT size: 2048<\/li>\n<li>Mag threshold: -90<\/li>\n<li>Max harmonics: 30<\/li>\n<li>f0 min: 150<\/li>\n<li>f0 max: 200<\/li>\n<\/ul>\n<h6>feature detection<\/h6>\n<ul>\n<li>time dependent<\/li>\n<li>Low level features: harmonicity, amplitude, fundamental frequency<\/li>\n<li>high level features: mood, genre, danceability<\/li>\n<\/ul>\n<p>Acoustic Brainz:\u00a0(typical analysis page)\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=17641\">https:\/\/reactivemusic.net\/?p=17641<\/a><\/p>\n<p>Essentia (open source feature detection tools) \u00a0<a href=\"https:\/\/github.com\/MTG\/essentia\">https:\/\/github.com\/MTG\/essentia<\/a><\/p>\n<p>Freesound (vast library of sounds): \u00a0<a href=\"https:\/\/www.freesound.org\">https:\/\/www.freesound.org<\/a>\u00a0&#8211; look at &#8220;similar sounds&#8221;<\/p>\n<h4>Removing voices from music<\/h4>\n<p>A sad thought<\/p>\n<h5>phase cancellation encryption<\/h5>\n<p>This method was used to send secret messages during world war 2. Its now used in cell phones to get rid of echo. Its also used in noise canceling headphones.<\/p>\n<p><a href=\"https:\/\/reactivemusic.net\/?p=8879\">https:\/\/reactivemusic.net\/?p=8879<\/a><\/p>\n<p><a style=\"color: #2795b6;\" href=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/12\/Screen-Shot-2013-12-31-at-8.38.13-PM.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-9035\" title=\"Screen Shot 2013-12-31 at 8.38.13 PM\" src=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/12\/Screen-Shot-2013-12-31-at-8.38.13-PM-300x169.png\" alt=\"\" width=\"300\" height=\"169\" srcset=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/12\/Screen-Shot-2013-12-31-at-8.38.13-PM-300x169.png 300w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/12\/Screen-Shot-2013-12-31-at-8.38.13-PM-500x282.png 500w, https:\/\/reactivemusic.net\/wp-content\/uploads\/2013\/12\/Screen-Shot-2013-12-31-at-8.38.13-PM.png 1019w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/p>\n<p>max-projects\/phase-cancellation\/phase-cancellation-example.maxpat<\/p>\n<h5>Center channel subtraction<\/h5>\n<p>What is not left and not right?<\/p>\n<p>Ableton Live &#8211; utility\/difference device:\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=1498\">https:\/\/reactivemusic.net\/?p=1498<\/a>\u00a0(Allison Krause example)<\/p>\n<p>Local file: Ableton-teaching-examples\/vocal-eliminator<\/p>\n<h4>More experiments<\/h4>\n<ul>\n<li>Synthesizing laughter\n<ul>\n<li><a href=\"https:\/\/reactivemusic.net\/?p=17314\">https:\/\/reactivemusic.net\/?p=17314<\/a><\/li>\n<li><a href=\"https:\/\/reactivemusic.net\/?p=17242\">https:\/\/reactivemusic.net\/?p=17242<\/a><\/li>\n<li><a href=\"https:\/\/reactivemusic.net\/?p=17239\">https:\/\/reactivemusic.net\/?p=17239<\/a><\/li>\n<\/ul>\n<\/li>\n<li>Bobby McFerrin: (pentatonic scale)\u00a0<a href=\"http:\/\/www.ted.com\/talks\/bobby_mcferrin_hacks_your_brain_with_music.html\">http:\/\/www.ted.com\/talks\/bobby_mcferrin_hacks_your_brain_with_music.html<\/a><\/li>\n<li>Alphabet vocals\n<ul>\n<li>jii lighter\u00a0<a href=\"https:\/\/reactivemusic.net\/?p=6970\">https:\/\/reactivemusic.net\/?p=6970<\/a><\/li>\n<li>Sesame St &#8211; Joan LaBarbara:\u00a0<a href=\"http:\/\/www.youtube.com\/watch?v=y819U6jBDog\">http:\/\/www.youtube.com\/watch?v=y819U6jBDog<\/a><\/li>\n<\/ul>\n<\/li>\n<li><span style=\"line-height: 1.6;\">Warping acapella tracks\u00a0<\/span><a style=\"line-height: 1.6;\" href=\"https:\/\/reactivemusic.net\/?p=18046\">https:\/\/reactivemusic.net\/?p=18046<\/a><\/li>\n<\/ul>\n<p><span style=\"font-size: 27px; font-weight: bold; line-height: 1.1;\">Questions<\/span><\/p>\n<ul>\n<li>Why do most people not like the recorded sound of their voice?<\/li>\n<li>Can voice be used as a controller?\n<ul>\n<li>(Imitone:\u00a0<a href=\"http:\/\/imitone.com\">http:\/\/imitone.com<\/a>)<\/li>\n<li>Mari Kimura<\/li>\n<\/ul>\n<\/li>\n<li>How do you recognize voices?<\/li>\n<li>Does speech recognition work with singing?<\/li>\n<li>How does the Google Speech API know the difference between music and speech?<\/li>\n<li>How can we listen to ultrasonic animal sounds?<\/li>\n<li>What about animal translators?<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A presentation for Berklee BTOT 2015\u00a0http:\/\/www.berklee.edu\/faculty (KITT dashboard by Dave Metlesits) The voice was the first musical instrument. Humans are not the only source of musical voices. Machines have voices. Animals too. Topics synthesizing voices (formant synthesis, text to speech, Vocaloid) processing voices (pitch-shifting, time-stretching, vocoding, filtering, harmonizing), voices of the natural world fictional languages &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/reactivemusic.net\/?p=17919\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Hearing voices&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","footnotes":""},"categories":[142],"tags":[34,323,346,345,128,190,176,138,13,137,298],"class_list":["post-17919","post","type-post","status-publish","format-standard","hentry","category-ideas","tag-ableton-live","tag-btot","tag-ideas","tag-maxmsp","tag-pd","tag-portfolio","tag-speech","tag-speech-to-text","tag-teaching","tag-text-to-speech","tag-voice"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Hearing voices - reactive music<\/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:\/\/reactivemusic.net\/?p=17919\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Hearing voices - reactive music\" \/>\n<meta property=\"og:description\" content=\"A presentation for Berklee BTOT 2015\u00a0http:\/\/www.berklee.edu\/faculty (KITT dashboard by Dave Metlesits) The voice was the first musical instrument. Humans are not the only source of musical voices. Machines have voices. Animals too. Topics synthesizing voices (formant synthesis, text to speech, Vocaloid) processing voices (pitch-shifting, time-stretching, vocoding, filtering, harmonizing), voices of the natural world fictional languages &hellip; Continue reading &quot;Hearing voices&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/reactivemusic.net\/?p=17919\" \/>\n<meta property=\"og:site_name\" content=\"reactive music\" \/>\n<meta property=\"article:published_time\" content=\"2015-01-02T02:24:04+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2015-01-15T23:15:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png\" \/>\n<meta name=\"author\" content=\"Tom Zicarelli\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Tom Zicarelli\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919\"},\"author\":{\"name\":\"Tom Zicarelli\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/#\\\/schema\\\/person\\\/56224d281582df7e5518e037ca63e571\"},\"headline\":\"Hearing voices\",\"datePublished\":\"2015-01-02T02:24:04+00:00\",\"dateModified\":\"2015-01-15T23:15:51+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919\"},\"wordCount\":1341,\"image\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/reactivemusic.net\\\/wp-content\\\/uploads\\\/2015\\\/01\\\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png\",\"keywords\":[\"Ableton Live\",\"BTOT\",\"ideas\",\"Max\\\/MSP\",\"Pd\",\"portfolio\",\"speech\",\"speech to text\",\"teaching\",\"text to speech\",\"voice\"],\"articleSection\":[\"ideas\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919\",\"url\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919\",\"name\":\"Hearing voices - reactive music\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/reactivemusic.net\\\/wp-content\\\/uploads\\\/2015\\\/01\\\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png\",\"datePublished\":\"2015-01-02T02:24:04+00:00\",\"dateModified\":\"2015-01-15T23:15:51+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/#\\\/schema\\\/person\\\/56224d281582df7e5518e037ca63e571\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/reactivemusic.net\\\/?p=17919\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#primaryimage\",\"url\":\"https:\\\/\\\/reactivemusic.net\\\/wp-content\\\/uploads\\\/2015\\\/01\\\/Screen-Shot-2015-01-09-at-10.01.42-PM.png\",\"contentUrl\":\"https:\\\/\\\/reactivemusic.net\\\/wp-content\\\/uploads\\\/2015\\\/01\\\/Screen-Shot-2015-01-09-at-10.01.42-PM.png\",\"width\":1622,\"height\":514},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/?p=17919#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/reactivemusic.net\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Hearing voices\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/#website\",\"url\":\"https:\\\/\\\/reactivemusic.net\\\/\",\"name\":\"reactive music\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/reactivemusic.net\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/reactivemusic.net\\\/#\\\/schema\\\/person\\\/56224d281582df7e5518e037ca63e571\",\"name\":\"Tom Zicarelli\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g\",\"caption\":\"Tom Zicarelli\"},\"sameAs\":[\"http:\\\/\\\/tomzicarelli.com\"],\"url\":\"https:\\\/\\\/reactivemusic.net\\\/?author=2\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Hearing voices - reactive music","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:\/\/reactivemusic.net\/?p=17919","og_locale":"en_US","og_type":"article","og_title":"Hearing voices - reactive music","og_description":"A presentation for Berklee BTOT 2015\u00a0http:\/\/www.berklee.edu\/faculty (KITT dashboard by Dave Metlesits) The voice was the first musical instrument. Humans are not the only source of musical voices. Machines have voices. Animals too. Topics synthesizing voices (formant synthesis, text to speech, Vocaloid) processing voices (pitch-shifting, time-stretching, vocoding, filtering, harmonizing), voices of the natural world fictional languages &hellip; Continue reading \"Hearing voices\"","og_url":"https:\/\/reactivemusic.net\/?p=17919","og_site_name":"reactive music","article_published_time":"2015-01-02T02:24:04+00:00","article_modified_time":"2015-01-15T23:15:51+00:00","og_image":[{"url":"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png","type":"","width":"","height":""}],"author":"Tom Zicarelli","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Tom Zicarelli","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/reactivemusic.net\/?p=17919#article","isPartOf":{"@id":"https:\/\/reactivemusic.net\/?p=17919"},"author":{"name":"Tom Zicarelli","@id":"https:\/\/reactivemusic.net\/#\/schema\/person\/56224d281582df7e5518e037ca63e571"},"headline":"Hearing voices","datePublished":"2015-01-02T02:24:04+00:00","dateModified":"2015-01-15T23:15:51+00:00","mainEntityOfPage":{"@id":"https:\/\/reactivemusic.net\/?p=17919"},"wordCount":1341,"image":{"@id":"https:\/\/reactivemusic.net\/?p=17919#primaryimage"},"thumbnailUrl":"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png","keywords":["Ableton Live","BTOT","ideas","Max\/MSP","Pd","portfolio","speech","speech to text","teaching","text to speech","voice"],"articleSection":["ideas"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/reactivemusic.net\/?p=17919","url":"https:\/\/reactivemusic.net\/?p=17919","name":"Hearing voices - reactive music","isPartOf":{"@id":"https:\/\/reactivemusic.net\/#website"},"primaryImageOfPage":{"@id":"https:\/\/reactivemusic.net\/?p=17919#primaryimage"},"image":{"@id":"https:\/\/reactivemusic.net\/?p=17919#primaryimage"},"thumbnailUrl":"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM-300x95.png","datePublished":"2015-01-02T02:24:04+00:00","dateModified":"2015-01-15T23:15:51+00:00","author":{"@id":"https:\/\/reactivemusic.net\/#\/schema\/person\/56224d281582df7e5518e037ca63e571"},"breadcrumb":{"@id":"https:\/\/reactivemusic.net\/?p=17919#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/reactivemusic.net\/?p=17919"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/reactivemusic.net\/?p=17919#primaryimage","url":"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM.png","contentUrl":"https:\/\/reactivemusic.net\/wp-content\/uploads\/2015\/01\/Screen-Shot-2015-01-09-at-10.01.42-PM.png","width":1622,"height":514},{"@type":"BreadcrumbList","@id":"https:\/\/reactivemusic.net\/?p=17919#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/reactivemusic.net\/"},{"@type":"ListItem","position":2,"name":"Hearing voices"}]},{"@type":"WebSite","@id":"https:\/\/reactivemusic.net\/#website","url":"https:\/\/reactivemusic.net\/","name":"reactive music","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/reactivemusic.net\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/reactivemusic.net\/#\/schema\/person\/56224d281582df7e5518e037ca63e571","name":"Tom Zicarelli","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/0da58cf21a2707dd335b204b8ed3cd9194dcbf9d9814ac5d71195a65c76c8a72?s=96&d=mm&r=g","caption":"Tom Zicarelli"},"sameAs":["http:\/\/tomzicarelli.com"],"url":"https:\/\/reactivemusic.net\/?author=2"}]}},"_links":{"self":[{"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/posts\/17919","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=17919"}],"version-history":[{"count":62,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/posts\/17919\/revisions"}],"predecessor-version":[{"id":18181,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=\/wp\/v2\/posts\/17919\/revisions\/18181"}],"wp:attachment":[{"href":"https:\/\/reactivemusic.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17919"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17919"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/reactivemusic.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17919"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}