Related papers: Unsupervised Learning and Representation of Mandar…

Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented. In this work, we use unsupervised representation learning to identify probable clusters of syllables that share…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics.…

Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language…

This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality in French and English vowels by applying the ciwGAN…

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of…

We propose an Encoder-Classifier framework to model the Mandarin tones using recurrent neural networks (RNN). In this framework, extracted frames of features for tone classification are fed in to the RNN and casted into a fixed dimensional…

This study asks how self-supervised speech models represent suprasegmental categories like Mandarin lexical tone, English lexical stress, and English phrasal accents. Through a series of probing tasks, we make layer-wise comparisons of…

This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2.0 with CTC, a method that has been successful in automatic speech recognition. We demonstrate that the method can improve the…

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…

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances,…

Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require sufficiently large labeled…

This article presents experiments performed using a computational laboratory environment for language acquisition experiments. It implements a multi-agent system consisting of two agents: an adult language model and a daughter language…

Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often modeled separately. Here, we test how encoding and decoding…

Recent improvements in Generative Adversarial Neural Networks (GANs) have shown their ability to generate higher quality samples as well as to learn good representations for transfer learning. Most of the representation learning methods…

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process.…

How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling unsupervised lexical learning from raw acoustic inputs,…

This study investigates how learners organize perceptual space in early phonetic acquisition by advancing previous studies in two key aspects. Firstly, it examines the shape of the learned hidden representation as well as its ability to…

In spontaneous speech, Mandarin tones that belong to the same tone category may exhibit many different contour shapes. We explore the use of data mining and NLP techniques for understanding the variability of tones in a large corpus of…

The study explored a new technique of phonetic tone training, which may have a positive impact on second language learning and tone training.