Results 11 to 20 of about 1,471,105 (229)
Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2022 Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural ...
Yusong Wu +5 more
semanticscholar +1 more source
Discovering and Mitigating Visual Biases Through Keyword Explanation [PDF]
Computer Vision and Pattern Recognition, 2023 Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample statistics, which ...
Younghyun Kim +5 more
semanticscholar +1 more source
Broadcasted Residual Learning for Efficient Keyword Spotting [PDF]
Interspeech, 2021 Keyword spotting is an important research field because it plays a key role in device wake-up and user interaction on smart devices. However, it is challenging to minimize errors while operating efficiently in devices with limited resources such as ...
Byeonggeun Kim +3 more
semanticscholar +1 more source
Keyword Transformer: A Self-Attention Model for Keyword Spotting [PDF]
Interspeech, 2021 The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or recurrent encoders.
Axel Berg, M. O'Connor, M. T. Cruz
semanticscholar +1 more source
PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords [PDF]
Interspeech, 2023 This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance.
Yong-Hyeok Lee, Namhyun Cho
semanticscholar +1 more source
Keyword-based Topic Modeling and Keyword Selection [PDF]
2021 IEEE International Conference on Big Data (Big Data), 2021 Certain type of documents such as tweets are collected by specifying a set of keywords. As topics of interest change with time it is beneficial to adjust keywords dynamically. The challenge is that these need to be specified ahead of knowing the forthcoming documents and the underlying topics.
Xingyu Wang 0003 +2 more
openaire +4 more sources
Deep Spoken Keyword Spotting: An Overview [PDF]
IEEE Access, 2021 Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago.
Iván López-Espejo +3 more
semanticscholar +1 more source
VocabulARy: Learning Vocabulary in AR Supported by Keyword Visualisations [PDF]
IEEE Transactions on Visualization and Computer Graphics, 2022 Learning vocabulary in a primary or secondary language is enhanced when we encounter words in context. This context can be afforded by the place or activity we are engaged with.
M. Weerasinghe +6 more
semanticscholar +1 more source
Education sciences, 2023 Although a significant body of research has accumulated on service learning over the past seven decades, to date, no reviews have analyzed the entire multi-disciplinary literature.
D. K. Narong, Phillip Hallinger
semanticscholar +1 more source
Keyword occurrences and journal specialization
Scientometrics, 2023 Since the borders of disciplines change over time and vary across communities and geographies, they can be expressed at different levels of granularity, making it challenging to find a broad consensus about the measurement of interdisciplinarity.
Gabriele Sampagnaro
semanticscholar +1 more source