SpeechRecorder

from Wikipedia, the free encyclopedia
SpeechRecorder

SpeechrecorderIcon.png
SpeechRecorderExperimenterView.tiff
Experimental view in SpeechRecorder
Basic data

Maintainer Institute for Phonetics and Speech Processing at the Ludwig Maximilians University in Munich
developer Christoph Draxler, Klaus Jänsch
Publishing year 2004
Current  version 2.6.1
(02/25/2013)
operating system Microsoft Windows, Mac OS X, Linux
programming language Java
category Audio recording
License LGPL 3.0
http://www.bas.uni-muenchen.de/Bas/software/speechrecorder/

SpeechRecorder is an open source and freely available software for script-controlled voice and audio recordings. It is mainly used for phonetic , linguistic or dialectological recordings, but also for speech therapy purposes or in the diagnosis of dysarthria .

SpeechRecorder presents a text, image or audio specification on the computer and records the speech signal of a speaker. SpeechRecorder supports two views of the recordings: in the speaker view the software shows a recording control in the form of a traffic light as well as the specifications to be processed, the experimenter view includes the speaker view plus a list of all elements of the current script, a signal display and others administrative information.

A recording script in SpeechRecorder is an XML document . A script is divided into sections, each containing individual recordings. The sections are presented sequentially, the recordings are processed sequentially or in random order. Each recording is written to a separate audio file in WAVE format. SpeechRecorder can either use the audio components known to the operating system or the audio components accessible via an ASIO driver. This enables recordings with two or more channels in parallel and with high signal quality.

SpeechRecorder was first presented in 2004 at the Language Resources and Evaluation Conference (LREC) in Lisbon. The software was developed in Java by Christoph Draxler and Klaus Jänsch at the Institute for Phonetics and Speech Processing at the Ludwig Maximilians University in Munich , and is under the LGPL 3.0 license. The current version is available on the pages of the Bavarian Archive for Speech Signals.

Individual evidence

  1. Christoph Draxler, Klaus Jänsch: SpeechRecorder - a Universal Platform Independent Multi-Channel Audio Recording Software. LREC, Lisbon 2004, pp. 559-562.
  2. Christoph Draxler, Klaus Jänsch: SpeechRecorder - multichannel voice recordings on the WWW. In: Advances in Acoustics. 2, (2005), pp. 741-742.
  3. ^ Website of the Institute for Phonetics and Speech Processing
  4. ^ Website of the Bavarian Archive for Speech Signals