English
Related papers

Related papers: Syllable Discovery and Cross-Lingual Generalizatio…

200 papers

Recent innovations in self-supervised representation learning have led to remarkable advances in natural language processing. That said, in the speech processing domain, self-supervised representation learning-based systems are not yet…

Computation and Language · Computer Science 2022-03-02 Hagai Aronowitz , Itai Gat , Edmilson Morais , Weizhong Zhu , Ron Hoory

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint…

Computer Vision and Pattern Recognition · Computer Science 2019-09-13 Chen Sun , Austin Myers , Carl Vondrick , Kevin Murphy , Cordelia Schmid

We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-01 Herman Kamper , Benjamin van Niekerk

Background: Computational models of speech recognition often assume that the set of target words is already given. This implies that these models do not learn to recognise speech from scratch without prior knowledge and explicit…

Computation and Language · Computer Science 2022-03-15 Danny Merkx , Sebastiaan Scholten , Stefan L. Frank , Mirjam Ernestus , Odette Scharenborg

Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec,…

Computation and Language · Computer Science 2024-10-18 Abdul Waheed , Hanin Atwany , Bhiksha Raj , Rita Singh

Syllable-level units offer compact and linguistically meaningful representations for spoken language modeling and unsupervised word discovery, but research on syllabification remains fragmented across disparate implementations, datasets,…

Computation and Language · Computer Science 2026-03-30 Héctor Javier Vázquez Martínez

We investigated word recognition in a Visually Grounded Speech model. The model has been trained on pairs of images and spoken captions to create visually grounded embeddings which can be used for speech to image retrieval and vice versa.…

Computation and Language · Computer Science 2020-06-02 Sebastiaan Scholten , Danny Merkx , Odette Scharenborg

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to…

Sound · Computer Science 2023-07-06 Chutong Meng , Junyi Ao , Tom Ko , Mingxuan Wang , Haizhou Li

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2017-08-22 Soravit Changpinyo , Wei-Lun Chao , Fei Sha

Visually grounded speech (VGS) models are trained on images paired with unlabelled spoken captions. Such models could be used to build speech systems in settings where it is impossible to get labelled data, e.g. for documenting unwritten…

Computation and Language · Computer Science 2022-10-13 Kayode Olaleye , Dan Oneata , Herman Kamper

We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Haotian Zhang , Pengchuan Zhang , Xiaowei Hu , Yen-Chun Chen , Liunian Harold Li , Xiyang Dai , Lijuan Wang , Lu Yuan , Jenq-Neng Hwang , Jianfeng Gao

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

Computation and Language · Computer Science 2023-08-22 Tim Hartill , Neset Tan , Michael Witbrock , Patricia J. Riddle

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Tilemachos Aravanis , Vladan Stojnić , Bill Psomas , Nikos Komodakis , Giorgos Tolias

Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Kanchana Ranasinghe , Brandon McKinzie , Sachin Ravi , Yinfei Yang , Alexander Toshev , Jonathon Shlens

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Computation and Language · Computer Science 2024-03-27 Chengxu Zhuang , Evelina Fedorenko , Jacob Andreas

This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two different channels (narrow and wide band). The joint…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-06 Vrunda N. Sukhadia , A. Arunkumar , S. Umesh

Keyword localisation is the task of finding where in a speech utterance a given query keyword occurs. We investigate to what extent keyword localisation is possible using a visually grounded speech (VGS) model. VGS models are trained on…

Computation and Language · Computer Science 2022-11-23 Kayode Olaleye , Dan Oneata , Herman Kamper

Automatic syllable count estimation (SCE) is used in a variety of applications ranging from speaking rate estimation to detecting social activity from wearable microphones or developmental research concerned with quantifying speech heard by…

Computation and Language · Computer Science 2019-09-04 Shreyas Seshadri , Okko Räsänen

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Johnathan Xie , Shuai Zheng

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode…

Computation and Language · Computer Science 2019-04-16 Herman Kamper , Aristotelis Anastassiou , Karen Livescu