Unsupervised Acoustic Unit Discovery By Leveraging A Language-independent Subword Discriminative Feature Representation

Abstract

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a subword-discriminative representation that is more language-independent. In the second stage, segment-level k-means is adopted, and two methods to represent the variable-length speech segments as fixed-dimension feature vectors are compared. Experiments on a very low-resource Mboshi language corpus show that our approach outperforms state-of-the-art AUD in both normalized mutual information (NMI) and

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyfeng2021unsupervised

Related papers

• An Empirical Evaluation Of Zero Resource Acoustic Unit Discovery (2017)0.00
• Exploiting Cross-lingual Speaker And Phonetic Diversity For Unsupervised Subword Modeling (2019)6.77
• The Effectiveness Of Unsupervised Subword Modeling With Autoregressive And Cross-lingual Phone-aware Networks (2020)2.26
• Unsupervised Word Segmentation And Lexicon Discovery Using Acoustic Word Embeddings (2016)12.10
• Word Segmentation On Discovered Phone Units With Dynamic Programming And Self-supervised Scoring (2022)9.23
• Unsupervised Acoustic Unit Discovery For Speech Synthesis Using Discrete Latent-variable Neural Networks (2019)9.59
• Combining Adversarial Training And Disentangled Speech Representation For Robust Zero-resource Subword Modeling (2019)7.16
• Unsupervised End-to-end Learning Of Discrete Linguistic Units For Voice Conversion (2019)9.03