UNTREF Speech Workshop
Talking To Machines
A short workshop introducing speech recognition and speech synthesis techniques for the creation of interactive artwork. We use pre-compiled open-source tools (CMU Sphinx ASR, Festival TTS, Processing, Python) and focus on the demonstrable strengths and unexpected limitations of speech technologies as vehicles for creating meaning.
Saturday Sept 21, 2-6pm Centro Cultural de Borges UNTREF.
- 1 Background Reading
- 2 Automatic Speech Recognition
- 2.1 Engines
- 2.2 Hands-on with Processing
- 2.3 Hands-on with Sphinx
- 2.4 Hands-on with Sphinx4 Library for Processing
- 2.5 Other programming
- 3 Text To Speech Synthesis
- 4 Activity: Feedback Loop
- Natalie Jeremijenko. "If Things Can Talk, What Do They Say? If We Can Talk To Things, What Do We Say?" 2005-03-05 [http://www.electronicbookreview.com/thread/firstperson/voicechip
- also see the responses by Simon Penny, Lucy Suchmann, and Natalie linked from that page.
- "Dialogue With A Monologue: Voice Chips and the Products of Abstract Speech". http://www.topologicalmedialab.net/xinwei/classes/readings/Jeremijenko/VoiceChips.pdf
- Mel Bochner. "Serial Art, Systems, Solipsism." (pdf)
Automatic Speech Recognition
- Talking to Machines.
- CMU Sphinx Open Source Toolkit For Speech Recognition Project by Carnegie Mellon University
- Pocketsphinx. A light-weight, portable implementatin of sphinx. pocketsphinx on win32 - http://www.aiaioo.com/cms/index.php?id=28
- Google ASR.
- Google ASR wrapped for processing - http://stt.getflourish.com/
Hands-on with Processing
- Download and install the STT library. http://dl.dropbox.com/u/974773/_keepalive/stt.zip
- Download the library file, unzip it, and copy it to the Processing\libraries folder.
Example - Listening with Google ASR
- Processing example:
- Try switching the recognition language. "es" vs. "en", "de", "fr".
Hands-on with Sphinx
- Download from sourceforge: http://cmusphinx.sourceforge.net/wiki/download/
- If using windows, you need the sphinxbase-0.8-win32.zip and pocketsphinx-0.8-win32.zip files. I already downloaded these for you. They are in the untref_speech folder.
- open a terminal. Windows, Run->Cmd.
- change to the pocketsphinx directory.
- ENGLISH: run the pocketsphinx command to recognize english:
pocketsphinx_continuous.exe -hmm ..\..\model\hmm\en_US\hub4wsj_sc_8k -dict ..\..\model\lm\en_US\cmu07a.dic -lm ..\..\model\lm\en_US\hub4.5000.DMP
- SPANISH: recognize spanish:
pocketsphinx_continuous.exe -hmm ..\..\model\hmm\es_MX\hub4_spanish_itesm.cd_cont_2500 -dict ..\..\model\lm\es_MX\h4.dict -lm ..\..\model\lm\es_MX\H4.arpa.Z.DMP
- this should transcribe live from the microphone.
- Acoustic models versus language models'.
- Grammars versus Statistical Language Models.
- Available language models for Sphinx:
- and more: http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/
Training your own Models
- grammer is trivial.
- slm, can use online tools. or try the sphinxtrain packages.
- the online tool http://www.speech.cs.cmu.edu/tools/lmtool-new.html
- upload a plain-text file of sentences. it will produce a language model from these!
- download the results.
- I can talk you through using the resultant model.
Hands-on with Sphinx4 Library for Processing
- This section includes a wrapper of the CMU Sphinx4 recognizer for Processing. Read more about the CMU Sphinx project at http://cmusphinx.sourceforge.net/.
- Below we have a library for processing, an example using a grammar of phrases for recognition, and one using a statistical language model.
- JAR file and some necessary language and acoustic models to do Sphinx-based speech recognition.
- Download the zip file below and copy it to your Processing/libraries folder:
Example - Grammar-based Recognition
- Simple grammar-based speech recognition with Sphinx4 in processing.
this example uses a simple grammar. In the data folder it has a grammar file (.gram), a dictionary file (.dict), and a config file (.xml) the grammar file (upstairs.gram) is a JSGF format grammar file that lists the possible words your system can hear. It has a format with individual words in upper-case letters, and a "|" mark between each word. You should be able to edit this file and fill it with your own words. the dict file (upstairs.dict) is a pronunciation dictionary file. It breaks each of those upper-case words fro the grammar into phonemic units. The easiest way to make a new dictionary with your own words is to use the online language tool described below. finally, the config file (upstairs.config.xml) specifies various parameters and file-names for the speech recognition engine. In this file you will probably need to change the path to your data files such as the grammar, dict, and the Library files you installed above. If you edit the xml file you will see that a lot of the paths are of the form "/Users/rtwomey/" which is obviously my computer, replace with the path to the file on your system. contact me if this doesn't work
Example - SLM-based Recognition
- This example does Sphinx4 automatic speech recognition using a statistical language model (SLM) rather than a grammar.
- I have included two SLMs in the data directory, 3990.lm/3990.dict, and 7707.lm/7707.dict
- They were generated with the CMU Sphinx Knowledge Base Tool (see below). For each, I uploaded a plain-text file of sentences and saved the resulting tar file with dict, lm, and other results.
- As above, you may need to change some file paths in the sphinx_config.xml file to match the setup on your system.
- Download file: http://wiki.dxarts.washington.edu/groups/general/wiki/d7564/attachments/01040/sphinxSLMTest.zip
Online Tool for Training Language Models
- This produces a statistical language model and dictionary (along with various other products) for the text you upload.
- Your source file should be plain text, one sentence per line.
- Upload the file and then click "Compile Knowledge Base."
- On the results screen, click on the .TAR file to download it. Unzip this file:
- The .dic is your pronunciation dictionary. You may want to rename it to .dict to match the files in the sketch. Or change your config file.
- The .lm file is a 3-gram SLM file. If you are trying the SLM example above you will need this as well.
- The grammar example above runs from a grammar (.gram) and a dictionary (.dict). This online language tools generates the dictionary for your text but not the grammar. You will need to make the grammar on your own.
- The SLM example above runs from a grammar (.gram) and a language model (.lm). This online tool generates both files.
- Sphinx Knowledge Base Tool: http://www.speech.cs.cmu.edu/tools/lmtool-new.html
- Python or c++
- command line
Text To Speech Synthesis
- Festival/Festvox. Festival from University of Edinburgh. CMU Speech group.
- freetts. wrapper for processing - http://www.local-guru.net/blog/pages/ttslib
- MARY TTS. http://mary.dfki.de/
- Google TTS. http://amnonp5.wordpress.com/2011/11/26/text-to-speech/
- Mac OS X Built in speech synthesis
- MBROLA voices. - http://tcts.fpms.ac.be/synthesis/
Test them online
- Festival online demo - http://www.cstr.ed.ac.uk/projects/festival/onlinedemo.html
- Spanish (UVIGO Spanish Male)
- American English
- MARY TTS online demo - http://mary.dfki.de:59125/
Hands-on With Processing
For Google TTS no library is required. You don't have to install anything. You just need an internet connection to talk to google.
Example 1. Speech
Example 2. Daisy Bell
- Daisy Bell - http://www.youtube.com/watch?v=41U78QP8nBk
- "Daisy Bell" was composed by Harry Dacre in 1892. In 1961, the IBM 7094 became the first computer to sing, singing the song Daisy Bell. Vocals were programmed by John Kelly and Carol Lockbaum and the accompaniment was programmed by Max Mathews.
- Processing Daisy Bell example using Google Text To Speech. Requires an internet connection:
Hands-on with Festival
- Tutorial - http://homepages.inf.ed.ac.uk/jyamagis/misc/Practice_of_Festival_speech_synthesizer.html
- windows binaries http://sourceforge.net/projects/e-guidedog/files/related%20third%20party%20software/0.3/festival-2.1-win.7z/download
- voices http://homepages.inf.ed.ac.uk/jyamagis/software/page54/page54.html
- Copy festival folder to C:\
- run the terminal. Start Menu, Run -> Cmd.
- switch to the festival directory:
- start festival:
- to say something:
(SayText "this is what I am going to say")
- to render speech to sound file:
- to switch voices:
- to exit festival:
- Festival is written in Scheme, a variant of LISP.
- spanish voices - http://sangonz.wordpress.com/2010/05/22/spanish-voices-for-festival/
Making a Voice
- Robert Voice
Activity: Feedback Loop
Construct a conversation with the machine.