An Iterative Deep Learning Framework For Unsupervised Discovery Of Speech Features And Linguistic Units With Applications On Spoken Term Detection

Abstract

In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech Challenge organized at Interspeech 2015. A Multi-layered Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets of acoustic tokens from the given corpus. Each acoustic token set is specified by a set of hyperparameters that describe the model configuration. These sets of acoustic tokens carry different characteristics fof the given corpus and the language behind, thus can be mutually reinforced. 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. Bottleneck features extracted from the MDNN are then used as the feedback input to the MAT and the MDNN itself in the next iteration. We call this iterative deep learning framework the Mult

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychung2016an

Related papers

• Unsupervised Iterative Deep Learning Of Speech Features And Acoustic Tokens With Applications To Spoken Term Detection (2017)0.00
• Self-supervised Language Learning From Raw Audio: Lessons From The Zero Resource Speech Challenge (2022)10.07
• The Zero Resource Speech Challenge 2020: Discovering Discrete Subword And Word Units (2020)11.58
• Unsupervised Acoustic Unit Discovery For Speech Synthesis Using Discrete Latent-variable Neural Networks (2019)9.59
• Unsupervised Neural And Bayesian Models For Zero-resource Speech Processing (2017)0.00
• Combining Adversarial Training And Disentangled Speech Representation For Robust Zero-resource Subword Modeling (2019)7.16
• Multilingual And Unsupervised Subword Modeling For Zero-resource Languages (2018)7.81
• Exploiting Cross-lingual Speaker And Phonetic Diversity For Unsupervised Subword Modeling (2019)6.77