Learn More
The aims of the SpeechDat-Car project are to develop a set of speech databases to support training and testing of multilingual speech recognition applications in the car environment. As a result, a total of ten (10) equivalent and similar resources will be created. The 10 languages are Danish, each language 600 sessions will be recorded (from at least 300(More)
SpeechRecorder is a platform independent audio recording software for speech corpus recordings. It is implemented in Java in a clean object-oriented design and adheres to established technology standards and document interchange formats. SpeechRecorder allows Unicode text and multimedia prompts, it supports audio recordings via more than two channels, and(More)
The goal of the SpeechDat project is to develop spoken language resources for speech recognisers suited to realise voice driven teleservices. SpeechDat created speech databases for all official languages of the European Union and some major dialectal varieties and minority languages. The size of the databases ranges between 500 and 5000 speakers. In total(More)
This paper gives an overview of the activities at the Bavarian Archive of Speech Signals (BAS) that was founded as a non-proot organization in 1995. The main purpose of BAS is the development of a Complete Phonetic Theory (CPT) of German based on the empirical exploitation of very large databases of spoken German. However, on our way to that goal BAS will(More)
The main purpose of this study was to compare acoustically the vowel spaces of two groups of cochlear implantees (CI) with two age-matched normal hearing groups. Five young test persons (15-25 years) and five older test persons (55-70 years) with CI and two control groups of the same age with normal hearing were recorded. The speech material consisted of(More)
We describe the pronunciation model of the automatic segmen-tation technique MAUS based on a data-driven Markov process and a new evaluation measure for phonemic transcripts relative symmetric accuracy; results are given for the MAUS segmenta-tion and labelling on German dialog speech. MAUS is currently distributed as a freeware package by the Bavarian(More)
In 2012 the Bavarian Archive for Speech Signals started providing some of its tools from the field of spoken language in the form of Software as a Service (SaaS). This means users access the processing functionality over a web browser and therefore do not have to install complex software packages on a local computer. Amongst others, these tools include(More)
The Bavarian Archive for Speech Signals has released three new speech corpora for both industrial and academic use: a) Hempels Sofa contains recordings of up to 60 seconds of non-scripted telephone speech, b) ZipTel is a corpus with telephone speech covering postal addresses and telephone numbers from a real world application, and c) RVG-J, an extension of(More)