Related papers: Automating Sound Change Prediction for Phylogeneti…
As a first step towards a complete computational model of speech learning involving perception-production loops, we investigate the forward mapping between pseudo-motor commands and articulatory trajectories. Two phonological feature sets,…
Phylogenetics is now fundamental in life sciences, providing insights into the earliest branches of life and the origins and spread of epidemics. However, finding suitable phylogenies from the vast space of possible trees remains…
Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a…
In recent years, image generation has shown a great leap in performance, where diffusion models play a central role. Although generating high-quality images, such models are mainly conditioned on textual descriptions. This begs the…
Traditional models of accent perception underestimate the role of gradient variations in phonological features which listeners rely upon for their accent judgments. We investigate how pretrained representations from current self-supervised…
Quartet Reconstruction, the task of recovering a phylogenetic tree from smaller trees on four species called \textit{quartets}, is a well-studied problem in theoretical computer science with far-reaching connections to statistics, graph…
In the human ear, the basilar membrane plays a central role in sound recognition. When excited by sound, this membrane responds with a frequency-dependent displacement pattern that is detected and identified by the auditory hair cells…
In recent years, there has been growing interest in representing speech with discrete tokens, which serve as pseudo-text for speech language models (speechLMs) and as efficient intermediate representations for downstream tasks. These tokens…
Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft…
Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level…
Sound event localization aims at estimating the positions of sound sources in the environment with respect to an acoustic receiver (e.g. a microphone array). Recent advances in this domain most prominently focused on utilizing deep…
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are…
In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use…
The various speech sounds of a language are obtained by varying the shape and position of the articulators surrounding the vocal tract. Analyzing their variations is crucial for understanding speech production, diagnosing speech disorders…
We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models on bottlenecks, we introduce a set of inductive biases…
We propose a model for evolution aiming to reproduce statistical features of fossil data, in particular the distributions of extinction events, the distribution of species per genus and the distribution of lifetimes, all of which are known…
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,…
Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep…
Recent advances in Large Language Models (LLMs) have shown promise in automating discourse annotation for conversations. While manually designing tree annotation schemes significantly improves annotation quality for humans and models, their…
Audio-language models have recently demonstrated strong zero-shot capabilities by leveraging natural-language supervision to classify audio events without labeled training data. Yet, their performance is highly sensitive to the wording of…