Proposed are a generative adversarial network-based voice bandwidth extender and extension method. A generative adversarial network-based voice bandwidth extension method, according to an embodiment, comprises the steps of: extracting feature vectors from a narrowband (NB) signal and a wideband (WB) signal of a voice; estimating the feature vector of the wideband signal from the feature vector of the narrowband signal; and learning a deep neural network classification model for discriminating the estimated feature vector of the wideband signal from the actually extracted feature vector of the wideband signal and the actually extracted feature vector of the narrowband signal.