Speech coding based on a multi-layer neural network

Shigeo Morishima*, Hiroshi Harashima, Yasuo Katayama


研究成果: Conference article査読

5 被引用数 (Scopus)


The authors present a speech-compression scheme based on a three-layer perceptron in which the number of units in the hidden layer is reduced. Input and output layers have the same number of units in order to achieve identity mapping. Speech coding is realized by scalar or vector quantization of hidden-layer outputs. By analyzing the weighting coefficients, it can be shown that speech coding based on a three-layer neural network is speaker-independent. Transform coding is automatically based on back propagation. The relation between compression ratio and SNR (signal-to-noise ratio) is investigated. The bit allocation and optimum number of hidden-layer units necessary to realize a specific bit rate are given. According to the analysis of weighting coefficients, speech coding based on a neural network is transform coding similar to Karhunen-Loeve transformation. The characteristics of a five-layer neural network are examined. It is shown that since the five-layer neural network can realize nonlinear mapping, it is more effective than the three-layer network.

ジャーナルConference Record - International Conference on Communications
出版ステータスPublished - 1990 12月 1
イベントIEEE International Conference on Communications - ICC '90 Part 2 (of 4) - Atlanta, GA, USA
継続期間: 1990 4月 161990 4月 19

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 電子工学および電気工学


「Speech coding based on a multi-layer neural network」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。