Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection

no code implementations • 17 Jul 2017 • Cheng-Tao Chung, Cheng-Yu Tsai, Chia-Hsiang Liu, Lin-shan Lee

A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets of acoustic tokens from the given corpus.

An Iterative Deep Learning Framework for Unsupervised Discovery of Speech Features and Linguistic Units with Applications on Spoken Term Detection

no code implementations • 1 Feb 2016 • Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Chia-Hsiang Liu, Hung-Yi Lee, Lin-shan Lee

The multiple sets of token labels are then used as the targets of a Multi-target Deep Neural Network (MDNN) trained on low-level acoustic features.

A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features

no code implementations • 7 Jun 2015 • Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Yuan-ming Liou, Yen-chen Wu, Yen-Ju Lu, Hung-Yi Lee, Lin-shan Lee

The Multi-layered Acoustic Tokenizer (MAT) proposed in this work automatically discovers multiple sets of acoustic tokens from the given corpus.