Related papers: What do End-to-End Speech Models Learn about Speak…
Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…
The field of speech processing has undergone a transformative shift with the advent of deep learning. The use of multiple processing layers has enabled the creation of models capable of extracting intricate features from speech data. This…
Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…
In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test…
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…
Do pretrained language models have knowledge regarding the surface information of tokens? We examined the surface information stored in word or subword embeddings acquired by pretrained language models from the perspectives of token length,…
Recent advances in self-supervised learning (SSL) on Transformers have significantly improved speaker verification (SV) by providing domain-general speech representations. However, existing approaches have underutilized the multi-layered…
Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…
This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…
While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…
In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by…
Analyses of self-supervised speech models have begun to reveal where and how they represent different types of information. However, almost all analyses have focused on English. Here, we examine how wav2vec2 models trained on four different…
Deep convolutional neural networks have achieved impressive performance on a broad range of problems, beating prior art on established benchmarks, but it often remains unclear what are the representations learnt by those systems and how…
Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…
Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task. In this paper we show the results…
Despite known differences between reading and listening in the brain, recent work has shown that text-based language models predict both text-evoked and speech-evoked brain activity to an impressive degree. This poses the question of what…
Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…
The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that surveyed such, are focused on high-level representation…
We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…