Related papers: A segmental framework for fully-unsupervised large…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…

Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), where the next frame…

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…

Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Recent advancements in speech-based topic segmentation have highlighted the potential of pretrained speech encoders to capture semantic representations directly from speech. Traditionally, topic segmentation has relied on a pipeline…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

We present a method for visually-grounded spoken term discovery. After training either a HuBERT or wav2vec2.0 model to associate spoken captions with natural images, we show that powerful word segmentation and clustering capability emerges…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an unsupervised manner.…

Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn such pixel-level alignment, current approaches typically rely…

Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the…

Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in the long-tail distribution and enabling multimodal learning…