BAS
Bavarian Archive for Speech Signals
Software

This page was last updated April 28th 2023

• BAS MAUS - Munich AUtomatic Segmentation

  MAUS is a tool to automatically segment and label speech into phonemic categories while anticipating statistical relevant variations in speech.

  MAUS is no longer distributed with full language support (only German), since the web-based MAUS system is now operational for several years - and also we encountered a number of illegal re-distributions of resources contained in the package by third parties.

• BAS EMU Speech Database Management System (EMU-SDMS)

  The EMU-SDMS is a collection of software tools which aims to be as close to an all-in-one solution for generating, manipulating, querying, analyzing and managing speech databases as possible.

  EMU-SDMS consists in it's core of two R Language packages emuR and wrassp, and uses the Emu webAPP tool as a front-end.

• BAS SpeechRecorder

  SpeechRecorder is a platform independent audio recording software customized to the requirements of speech recordings.

• Munich Automatic Speaker Verification (MASV)

  MASV is a complete experimental environment for testing speaker verification techniques. It was designed for the German VeriDat corpus, but myay be adapted to other corpora. It requires MatLab.

• BAS WebTranscribe

  WebTranscribe is JAVA Webstart based client application that together with a JAVA servlet and a standard data base tool allows to annotate vast amounts of speech data over the Web. The tool downloads the next free speech sample, displays it and offers a customizable text editor for transcription. The servlet takes care of locking and storage of the annotation information into the database.

  WebTranscribe is currently (02/2005) under development (Beta) and is used in several BAS internal projects (e.g. SmartWeb data collection). If you are interested in using WebTranscribe for your speech resource project, please contact Christoph Draxler at BAS.