In this work we describe a new method that adjusts time-delays and the widths of time-windows in artificial neural networks automatically. The input of the units are weighted by a gaussian input-window over time which allows the learning rules for the delays and widths to be derived in the same way as it is used for the weights. Our results on a phoneme classification task compare well with res...

This paper deals with methods for finding the suitable weights in an Artificial Neural Network (ANN) using Genetic Algorithms (GA).We study the weakness and strengthness of the proposed approach in case of a statistical data forecasting. We describe a different approach when using the input data during optimization phase. Besides GA, we applied stationary wavelet transform (SWT) as a signal pre...

In this article, we describe the OCR and image processing algorithms used to read destination addresses from nonstandard letters (flats) by the Siemens postal automation system currently in use by the Deutsche Post AG.The article concentrates mainly on the two classifiers used to recognize handprinted digits. One of them is a complex time delayed neural network (TDNN) used to classify scaled di...

Recognition of spelled names over the telephone line is essential for applications such as telephone directory assistance, or automatic mail ordering. We present recognition results on the spelling section of the OGI Spelled and Spoken Word Telephone Corpus, using a Multi-State Time Delay Neural Network (MS-TDNN). Many applications allow for strong language modeling constraints. In our experime...

Corrigendum: Gas-bearing Prediction of Deep Reservoir Based on DNN EmbeddingsShuying Ma1, 2, 3, Junxing Cao1, 3*, Zhege Liu4, 5, Xudong Jiang1, Zhaodong Su1, Yajuan Xue4, 5* Correspondence: [email protected]: gas-bearing prediction, Cepstrum, Embedding, TDNN, LSTM, deep reservoirsCorrigendum on: Ma, S., Cao, J., Liu, Z., Jiang, X., Su, and Xue, Y. (2023). prediction reservoir based embe...

In this study, a complete system that generates visual speech by synthesizing 3D face points has been implemented. The estimated face points drive MPEG-4 facial animation. This system is speaker independent and can be driven by audio or both audio and text. The synthesis of visual speech was realized by a codebook-based technique, which is trained with audio-visual data from a speaker. An audio...

This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice quality produced by this system compares...

State-of-the-art automatic speech recognition (ASR) system development is data and computation intensive. The optimal design of deep neural networks (DNNs) for these systems often require expert knowledge empirical evaluation. In this paper, a range architecture search (NAS) techniques are used to automatically learn two types hyper-parameters factored time delay (TDNN-Fs): i) the left right sp...

We deene a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma lters (as proposed by de Vries and Principe (de Vries & Principe 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We nd that both the inclusion of gamma lters in all layers, and the...