Unsupervised Discovery of Structured Acoustic Tokens with Applications to Spoken Term Detection

11/28/2017

∙

In this paper, we compare two paradigms for unsupervised discovery of structured acoustic tokens directly from speech corpora without any human annotation. The Multigranular Paradigm seeks to capture all available information in the corpora with multiple sets of tokens for different model granularities. The Hierarchical Paradigm attempts to jointly learn several levels of signal representations in a hierarchical structure. The two paradigms are unified within a theoretical framework in this paper. Query-by-Example Spoken Term Detection (QbE-STD) experiments on the QUESST dataset of MediaEval 2015 verifies the competitiveness of the acoustic tokens. The Enhanced Relevance Score (ERS) proposed in this work improves both paradigms for the task of QbE-STD. We also list results on the ABX evaluation task of the Zero Resource Challenge 2015 for comparison of the Paradigms.

READ FULL TEXT

Unsupervised Discovery of Structured Acoustic Tokens with Applications to Spoken Term Detection

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

Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings

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

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

A Nonparametric Bayesian Approach for Spoken Term detection by Example Query

Unsupervised Spoken Term Detection with Spoken Queries by Multi-level Acoustic Patterns with Varying Model Granularity

Enhancing Automatically Discovered Multi-level Acoustic Patterns Considering Context Consistency With Applications in Spoken Term Detection

Unsupervised Discovery of Structured Acoustic Tokens with Applications to Spoken Term Detection

Related Research

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

Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings

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

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

A Nonparametric Bayesian Approach for Spoken Term detection by Example Query

Unsupervised Spoken Term Detection with Spoken Queries by Multi-level Acoustic Patterns with Varying Model Granularity

Enhancing Automatically Discovered Multi-level Acoustic Patterns Considering Context Consistency With Applications in Spoken Term Detection