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

04/01/2018

∙

Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as query-by-example Spoken Term Detection (STD), the lack of mapping relationships between these discovered tokens and real phonemes have limited the down-stream applications. This paper represents probably the first attempt towards the goal of completely unsupervised phoneme recognition, or mapping audio signals to phoneme sequences without phoneme-labeled audio data. The basic idea is to cluster the embedded acoustic tokens and learn the mapping between the cluster sequences and the unknown phoneme sequences with a Generative Adversarial Network (GAN). An unsupervised phoneme recognition accuracy of 36

READ FULL TEXT

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

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

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

Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection

A segmental framework for fully-unsupervised large-vocabulary speech recognition

Query-by-example Spoken Term Detection using Attention-based Multi-hop Networks

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

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

Related Research

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

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

Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection

A segmental framework for fully-unsupervised large-vocabulary speech recognition

Query-by-example Spoken Term Detection using Attention-based Multi-hop Networks

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