Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

On DNN posterior probability combination in multi-stream speech recognition for reverberant environments

: Xiong, F.; Goetze, S.; Meyer, B.T.


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society:
IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017. Proceedings : March 5-9, 2017, Hilton New Orleans Riverside, New Orleans, Louisiana, USA
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-4117-6
ISBN: 978-1-5090-4116-9
ISBN: 978-1-5090-4118-3
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) <42, 2017, New Orleans/La.>
Fraunhofer IDMT ()

A multi-stream framework with deep neural network (DNN) classifiers has been applied in this paper to improve automatic speech recognition (ASR) performance in environments with different reverberation characteristics. We propose a room parameter estimation model to determine the stream weights for DNN posterior probability combination with the aim of obtaining reliable log-likelihoods for decoding. The model is implemented by training a multi-layer perceptron to distinguish between various reverberant environments. The method is tested in known and unknown environments against approaches based on inverse entropy and autoencoders, with average relative word error rate improvements of 46% and 29%, respectively, when performing multi-stream ASR in different reverberant situations.