English
Related papers

Related papers: Speech-to-See: End-to-End Speech-Driven Open-Set O…

200 papers

Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning. To this end, we introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Triantafyllos Afouras , Andrew Owens , Joon Son Chung , Andrew Zisserman

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract…

Computation and Language · Computer Science 2012-07-03 Cynthia Matuszek , Nicholas FitzGerald , Luke Zettlemoyer , Liefeng Bo , Dieter Fox

In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-26 Yael Segal , Tzeviya Sylvia Fuchs , Joseph Keshet

This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on a task-related prompt for audio data. We pre-train the…

Computation and Language · Computer Science 2023-09-12 Aobo Xia , Shuyu Lei , Yushu Yang , Xiang Guo , Hua Chai

This paper explores the possibility of using visual object detection techniques for word localization in speech data. Object detection has been thoroughly studied in the contemporary literature for visual data. Noting that an audio can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Mohammad Samragh , Arnav Kundu , Ting-Yao Hu , Minsik Cho , Aman Chadha , Ashish Shrivastava , Oncel Tuzel , Devang Naik

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and…

Computation and Language · Computer Science 2021-05-12 Pengwei Wang , Xin Ye , Xiaohuan Zhou , Jinghui Xie , Hao Wang

Service robots are expected to operate effectively in human-centric environments for long periods of time. In such realistic scenarios, fine-grained object categorization is as important as basic-level object categorization. We tackle this…

Computer Vision and Pattern Recognition · Computer Science 2019-07-31 S. Hamidreza Kasaei

This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Wenhao Cheng , Junbo Yin , Wei Li , Ruigang Yang , Jianbing Shen

We propose Attention Grounder (AttnGrounder), a single-stage end-to-end trainable model for the task of visual grounding. Visual grounding aims to localize a specific object in an image based on a given natural language text query. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Vivek Mittal

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…

Sound · Computer Science 2018-05-16 Hiroshi Seki , Takaaki Hori , Shinji Watanabe , Jonathan Le Roux , John R. Hershey

The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new word learning, it…

Computation and Language · Computer Science 2024-12-30 Ziqiao Ma , Jiayi Pan , Joyce Chai

Speech-to-text translation pertains to the task of converting speech signals in a language to text in another language. It finds its application in various domains, such as hands-free communication, dictation, video lecture transcription,…

Computation and Language · Computer Science 2024-06-11 Nivedita Sethiya , Chandresh Kumar Maurya

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when modeling language to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Heng Zhao , Joey Tianyi Zhou , Yew-Soon Ong

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Computation and Language · Computer Science 2019-02-20 Shruti Palaskar , Vikas Raunak , Florian Metze

With the development of internet of things technologies, tremendous sensor audio data has been produced, which poses great challenges to audio-based event detection in smart cities. In this paper, we target a challenging audio-based event…

Sound · Computer Science 2023-12-27 Haoyu Tang , Yunxiao Wang , Jihua Zhu , Shuaike Zhang , Mingzhu Xu , Qinghai Zheng , Yupeng Hu

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are…

Machine Learning · Computer Science 2016-12-19 Yannis M. Assael , Brendan Shillingford , Shimon Whiteson , Nando de Freitas

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic…

Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is…

Sound · Computer Science 2025-01-10 Darius Petermann , Mahdi M. Kalayeh

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…

Computation and Language · Computer Science 2019-07-11 Wei-Ning Hsu , David Harwath , James Glass

Language is an interface to the outside world. In order for embodied agents to use it, language must be grounded in other, sensorimotor modalities. While there is an extended literature studying how machines can learn grounded language, the…

Artificial Intelligence · Computer Science 2021-10-12 Tristan Karch , Laetitia Teodorescu , Katja Hofmann , Clément Moulin-Frier , Pierre-Yves Oudeyer