Neural networks for pattern recognition with applications to acoustics and speech.

Spatio-Temporal Pattern Recognition with Neural Networks: Application to Speech

The processing or the recognition of non stationary process with neural networks is a challenging and yet unsolved issue. The paper discuss the general pattern recognition framework using neural networks in relation with the understanding of the peripheral auditory system. We propose a short-time structure representation of speech for speech analysis and recognition. We give examples of neural ...

Automatic Speech Recognition with Deep Neural Networks for Impaired Speech

Automatic Speech Recognition has reached almost human performance in some controlled scenarios. However, recognition of impaired speech is a difficult task for two main reasons: data is (i) scarce and (ii) heterogeneous. In this work we train different architectures on a database of dysarthric speech. A comparison between architectures shows that, even with a small database, hybrid DNN-HMM mode...

Pattern Recognition and Neural Networks

Hidden neural networks: application to speech recognition

In this paper we evaluate the Hidden Neural Network HMM/NN hybrid presented at last years ICASSP on two speech recognition benchmark tasks; 1) task independent isolated word recognition on the PHONEBOOK database, and 2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how Hidden Neural Networks (HNNs) with much fewer parameters than conventional HMM...

Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge

Regis Cardin Dept Computer Science McGill University We attempt to combine neural networks with knowledge from speech science to build a speaker independent speech recognition system. This knowledge is utilized in designing the preprocessing, input coding, output coding, output supervision and architectural constraints. To handle the temporal aspect of speech we combine delays, copies of activa...