Finn Tore Johansen

Learn More
An important aspect of noise robustness of automatic speech recognisers (ASR) is the proper handling of non-speech acoustic events. The present paper describes further improvements of an already existing reference recogniser towards achieving such kind of robustness. The reference recogniser applied is the COST 249 SpeechDat reference recogniser, which is a(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)
The COST 249 SpeechDat reference recogniser is a fully automatic, language-independent training procedure for building a phonetic recogniser. It relies on the HTK toolkit and a SpeechDat(II) compatible database. The recogniser is designed to serve as a reference system in multilingual recognition research. This paper documents version 0.93 of the reference(More)
This paper presents a comparison of di erent model architectures for TIMIT phoneme recognition. The baseline is a conventional diagonal covariance Gaussian mixture HMM. This system is compared to two di erent hybrid MLP/HMMs, both adhering to the same restrictions regarding input context and output states as the Gaussian mixtures. All free parameters in the(More)
The paper describes our ongoing work on crosslingual speech recognition based on multilingual triphone hidden Markov models. Multilingual acoustic models were built using two different clustering procedures: agglomerative triphone clustering and tree-based triphone clustering. The agglomerative clustering procedure is based on measuring the similarity of(More)