Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Data-driven speech processing models usually perform well with a large amount of text
supervision, but collecting transcribed speech data is costly. Therefore, we propose Speech …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …

Recent work on unsupervised speech segmentation has used self-supervised models with
phone and word segmentation modules that are trained jointly. This paper instead revisits …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
producing performance and data efficiency improvements for a variety of speech tasks …

Abstract Large Language Models (LLMs) have been criticized for failing to connect linguistic
meaning to the world—for failing to solve the “symbol grounding problem.” Multimodal Large …

We propose a novel framework for target speech extraction based on semantic information,
called ConceptBeam. Target speech extraction means extracting the speech of a target …

We present DenseAV a novel dual encoder grounding architecture that learns high-
resolution semantically meaningful and audio-visual aligned features solely through …

We study phrase structure induction from visually-grounded speech. The core idea is to first
segment the speech waveform into sequences of word segments, and subsequently induce …

Language models require tokenized inputs. However, tokenization strategies for continuous
data like audio and vision are often based on simple heuristics such as fixed sized …