Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Distant-Talking Continuous Speech Recognition Based on a Novel Reverberation Model in the Feature Domain

Armin Sehr, Marcus Zeller, Walter Kellermann

Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

A novel approach for automatic speech recognition in highly reverberant environments, proposed in [1] for isolated word recognition, is extended to continuous speech recognition (CSR) in this paper. The approach is based on a combined acoustic model consisting of a network of clean speech HMMs and a reverberation model. Because the grammatical information and the information about the acoustic environment are strictly separated in the combined model, a high degree of flexibility for adapting the system to new tasks and new environments is attained. We show that virtually all known CSR search algorithms can be used for decoding the proposed combined model if a few extensions are added. In a simulation of a connected digit recognition task, the proposed method achieves more than 40% reduction of the word error rate compared to a conventional HMM-based system trained on reverberant speech, at the cost of an increased decoding complexity.

Full Paper

Bibliographic reference.  Sehr, Armin / Zeller, Marcus / Kellermann, Walter (2006): "Distant-talking continuous speech recognition based on a novel reverberation model in the feature domain", In INTERSPEECH-2006, paper 1111-Tue1A2O.1.