UNTREF Speech Workshop

<<< back to Wiki Home

Contents

Introduction

A short 1-2 day workshop introducing speech recognition and speech synthesis techniques for the creation of interactive artwork. We use pre-compiled open-source tools (CMU Sphinx ASR and Festival TTS), and focus on the specifics of language model construction and creative deployment of the technologies as vehicles for creating meaning.

Background

• If Things Can Talk, What Do They Say? If We Can Talk to Things, What Do We Say? Natalie Jeremijenko. 2005-03-05 [1]
  • also see the responses by Simon Penny, Lucy Suchmann, and Natalie.
• Dialogue with a Monologue: Voice Chips and the Products of Abstract Speech. [2]

Speech Recognition

Introduction

• pocketsphinx on win32 - http://www.aiaioo.com/cms/index.php?id=28

Installing CMU Sphinx

http://cmusphinx.sourceforge.net/wiki/download/

Language Models

Acoustic models versus language models.

Grammars versus Satistical Language Models.

Using sphinx

• open a terminal. Windows, Run->Cmd.
• change to the pocketsphinx directory.
  • cd Desktop\untref_speech\pocketsphinx-0.8-win32\bin\Release
• run the pocketsphinx command:
  • 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
  • this should transcribe live from the microphone.

Training your own Models

grammer is trivial.

slm, can use online tools. or try the sphinxtrain packages.

Programming with Speech Recognition

Processing. Sphinx4, the java interface.

Python or c++, command line, android. pocketsphinx.

Speech Synthesis

Introduction

FestVox. CMU Speech group.

Festival from University of Edinburgh.

Installation

• http://festvox.org/packed/festival/2.1/festival-2.1-release.tar.gz