Time Delay Neural Network (TDNN) is a well-performing structure for deep neural network-based speaker recognition systems. In this paper we introduce novel structure, named Crossed-Time (CTDNN) to enhance the performance of current TDNN recognition. Inspired by multi-filters setting convolution layers from networks, set multiple time delay units with different context size at bottom layer and c...

We propose an algorithm based on a time delay neural network (TDNN) with spatio-temporal receptive elds for segementationfree detection of overtaking vehicles on motorways. Our algorithm transforms the detection problem into a classi cation problem of strongly downscaled image sequences which serve as an input to the TDNN without a preliminary segmentation step. The TDNN classi er is followed b...

This paper investigates the use of perceptually-motivated subband temporal envelope (STE) features and time-delay neural network (TDNN) denoising autoencoder (DAE) to improve deep neural network (DNN)-based automatic speech recognition (ASR). STEs are estimated by full-wave rectification and low-pass filtering of band-passed speech using a Gammatone filter-bank. TDNNs are used either as DAE or ...

In this paper we investigate a time delay neural network (TDNN) for a keyword spotting task that requires low CPU, memory and latency. The TDNN is trained with transfer learning and multi-task learning. Temporal subsampling enabled by the time delay architecture reduces computational complexity. We propose to apply singular value decomposition (SVD) to further reduce TDNN complexity. This allow...

In reverberant environments there are long term interactions between speech and corrupting sources. In this paper a time delay neural network (TDNN) architecture, capable of learning long term temporal relationships and translation invariant representations, is used for reverberation robust acoustic modeling. Further, iVectors are used as an input to the neural network to perform instantaneous ...

Air pollution is a challenging issue in some of the large cities in developing countries. Air quality monitoring and interpretation of data are two important factors for air quality management in urban areas. Several methods exist to analyze air quality. Among them, we applied the dynamic neural network (TDNN) and Radial Basis Function (RBF) methods to predict the concentrations of ground-level...

air pollution is a challenging issue in some of the large cities in developing countries. air quality monitoring and interpretation of data are two important factors for air quality management in urban areas. several methods exist to analyze air quality. among them, we applied the dynamic neural network (tdnn) and radial basis function (rbf) methods to predict the concentrations of ground-level...

Air pollution is a challenging issue in some of the large cities in developing countries. Air quality monitoring and interpretation of data are two important factors for air quality management in urban areas. Several methods exist to analyze air quality. Among them, we applied the dynamic neural network (TDNN) and Radial Basis Function (RBF) methods to predict the concentrations of ground-level...

Alex Waibel Carnegie Mellon University Pittsburgh, PA 15213 [email protected] We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition. Unlike most other hybrid methods. the MS-TDNN embeds an alignment search procedure into the connectionist architecture. and allows for word level supervision. The resulting system has the ability to ma...

Yann Le Cun AT&T Bell Laboratories 101 Crawford Corner Rd Holmdel, NJ 07733 The backpropagation algorithm can be used for both recognition and generation of time trajectories. When used as a recognizer, it has been shown that the performance of a network can be greatly improved by adding structure to the architecture. The same is true in trajectory generation. In particular a new architecture c...