Related papers: A tentative model for dimensionless phoneme distan…
We describe a new method for estimating the degree of "transientness" and "tonality" of a class of compound signals involving simultaneously transient and harmonic features. The key assumption is that both transient and tonal layers admit…
Acoustic-prosodic entrainment describes the tendency of humans to align or adapt their speech acoustics to each other in conversation. This alignment of spoken behavior has important implications for conversational success. However,…
We probe the layers in multilingual BERT (mBERT) for phylogenetic and geographic language signals across 100 languages and compute language distances based on the mBERT representations. We 1) employ the language distances to infer and…
This paper presents a general study of one-dimensional differentiability for functionals defined on convex domains that are not necessarily open. The local approximation is carried out using affine functionals, as opposed to linear…
The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the…
Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…
(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…
Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…
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…
Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…
We survey the emerging area of compression-based, parameter-free, similarity distance measures useful in data-mining, pattern recognition, learning and automatic semantics extraction. Given a family of distances on a set of objects, a…
For many optimization problems it is possible to define a distance metric between problem variables that correlates with the likelihood and strength of interactions between the variables. For example, one may define a metric so that the…
In this paper, we introduce a neural network-based method for regional speech separation using a microphone array. This approach leverages novel spatial cues to extract the sound source not only from specified direction but also within…
One of the many tasks facing the typically-developing child language learner is learning to discriminate between the distinctive sounds that make up words in their native language. Here we investigate whether multimodal…
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related…
The use of phonological features (PFs) potentially allows language-specific phones to remain linked in training, which is highly desirable for information sharing for multilingual and crosslingual speech recognition methods for…
With the rise of Speech Large Language Models (Speech LLMs), there has been growing interest in discrete speech tokens for their ability to integrate with text-based tokens seamlessly. Compared to most studies that focus on continuous…
The quantale of distance distributions is of fundamental importance for understanding probabilistic metric spaces as enriched categories. Motivated by the categorical interpretation of partial metric spaces, we are led to investigate the…
The pure tone hearing threshold is usually estimated from responses to stimuli at a set of standard frequencies. This paper describes a probabilistic approach to the estimation problem in which the hearing threshold is modelled as a smooth…
In a scenario with multiple persons talking simultaneously, the spatial characteristics of the signals are the most distinct feature for extracting the target signal. In this work, we develop a deep joint spatial-spectral non-linear filter…