Related papers: Analyzing autoencoder-based acoustic word embeddin…

Transformer language models encode the notion of word order using positional information. Most commonly, this positional information is represented by absolute position embeddings (APEs), that are learned from the pretraining data. However,…

Understanding the neural mechanisms behind auditory and linguistic processing is key to advancing cognitive neuroscience. In this study, we use Magnetoencephalography (MEG) data to analyze brain responses to spoken language stimuli. We…

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data…

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…

In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised…

The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music and environmental sounds. To approach this problem, methods inspired by works on…

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to build an automatic speech recognition (ASR) system for the target low-resource language. We compare this to using acoustic word embedding…

Acoustic Word Embeddings (AWEs) improve the efficiency of speech retrieval tasks such as Spoken Term Detection (STD) and Keyword Spotting (KWS). However, existing approaches suffer from limitations, including unimodal supervision, disjoint…

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…

Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic. However, these vector space representations (created through large-scale…

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be…

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

This paper compares machine learning approaches with different input data formats for the classification of acoustic emission (AE) signals. AE signals are a promising monitoring technique in many structural health monitoring applications.…

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate…

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…