Completely Unsupervised Phoneme Recognition By Adversarially Learning Mapping Relationships From Audio Embeddings

Abstract

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% was achieved in the preliminary experiments.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2018completely

Related papers

• Generative Adversarial Phonology: Modeling Unsupervised Phonetic And Phonological Learning With Neural Networks (2020)10.07
• Unsupervised Word Segmentation And Lexicon Discovery Using Acoustic Word Embeddings (2016)12.10
• Robust Speech Recognition Using Generative Adversarial Networks (2017)11.29
• Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models (2019)9.23
• Towards Unsupervised Speech Recognition Without Pronunciation Models (2024)0.00
• Unsupervised Speech Recognition Via Segmental Empirical Output Distribution Matching (2018)0.00
• Efficient Acoustic Feature Transformation In Mismatched Environments Using A Guided-gan (2022)2.26
• Audio Word2vec: Unsupervised Learning Of Audio Segment Representations Using Sequence-to-sequence Autoencoder (2016)0.00