𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Performance comparison of neural network architectures for speaker-independent phoneme recognition

✍ Scribed by Satoru Nakamura; Hidefumi Sawai

Publisher
John Wiley and Sons
Year
1992
Tongue
English
Weight
790 KB
Volume
23
Category
Article
ISSN
0882-1666

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

We applied several types of time‐delay neural networks (TDNNs), generally used for speaker‐dependent and multispeaker speech recognition, to speaker‐independent speech recognition and compared their performance. Six or 12 speakers were used to train each network, and recognition experiments for voiced stops /b, d, g/ were performed in open speaker mode. The best recognition rates were 91.3 percent and 93.6 percent, using six and 12 training speakers, respectively. We found that constructing modular networks, such as modular TDNN with each network corresponding to a speaker, is effective in terms of decreasing the number of training iterations needed, showing slightly better performance than with a single TDNN with a comparable network capacity. This is because the modular networks make use of limited capacity effectively. On the other hand, a single TDNN with an increased number of hidden units showed a recognition rate comparable to that of the modular TDNN.

πŸ“œ SIMILAR VOLUMES

Flexible vowel recognition by the genera
Flexible vowel recognition by the generation of dynamic coherence in oscillator neural networks: speaker-independent vowel recognition
✍ Fang Liu; Yoko Yamaguchi; Hiroshi Shimizu πŸ“‚ Article πŸ“… 1994 πŸ› Springer-Verlag 🌐 English βš– 947 KB

We propose a new model for speaker-independent vowel recognition which uses the flexibility of the dynamic linking that results from the synchronization of oscillating neural units. The system consists of an input layer and three neural layers, which are referred to as the A-, B-and C-centers. The i

Comparing performance of spectral distan
Comparing performance of spectral distance measures and neural network methods for vowel recognition
✍ Candace A. Kamm; Lynn A. Streeter; Yana Kane-Esrig; David J. Burr πŸ“‚ Article πŸ“… 1989 πŸ› Elsevier Science 🌐 English βš– 983 KB

Neural networks were trained to classify single 20 ms frames of vowels using either perceptually-based spectral representations or LPC spectra as input. Classification performance was compared with performance of several distance measures using nearest-neighbor and mean-distance decision criteria. T

Comparison of the performance of neural
Comparison of the performance of neural network methods and Cox regression for censored survival data
✍ Anny Xiang; Pablo Lapuerta; Alex Ryutov; Jonathan Buckley; Stanley Azen πŸ“‚ Article πŸ“… 2000 πŸ› Elsevier Science 🌐 English βš– 99 KB

Strategies that have been developed to extend NN prediction methods to accommodate right-censored data include methods due to Faraggi-Simon, Liestol-Andersen-Andersen, and a modiΓΏcation of the Buckley-James method. In a Monte Carlo simulation study, we evaluated the performance of all three NN metho

Optimal artificial neural network archit
Optimal artificial neural network architecture selection for performance prediction of compact heat exchanger with the EBaLM-OTR technique
✍ Dumidu Wijayasekara; Milos Manic; Piyush Sabharwall; Vivek Utgikar πŸ“‚ Article πŸ“… 2011 πŸ› Elsevier Science 🌐 English βš– 841 KB

Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it