Results 71 to 80 of about 288,136 (202)

Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting

, 2017
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements.
Fu, Gengshen, Mandal, Arindam, Matsoukas, Spyros, Panchapagesan, Sankaran, Raju, Anirudh, Strom, Nikko, Sun, Ming, Tucker, George, Vitaladevuni, Shiv   +8 more
core   +1 more source

Joint intent detection and slot filling with syntactic and semantic features using multichannel CNN-BiLSTM [PDF]

PeerJ Computer Science
Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU).
Yusuf Idris Muhammad, Naomie Salim, Anazida Zainal   +2 more
doaj   +2 more sources

Speaker-following Video Subtitles

, 2014
We propose a new method for improving the presentation of subtitles in video (e.g. TV and movies). With conventional subtitles, the viewer has to constantly look away from the main viewing area to read the subtitles at the bottom of the screen, which ...
Hu, Yongtao, Kautz, Jan, Wang, Wenping, Yu, Yizhou   +3 more
core   +1 more source

Evaluation of spoken document retrieval for historic speech collections [PDF]

, 2008
The re-use of spoken word audio collections maintained by audiovisual archives is severely hindered by their generally limited access. The CHoral project, which is part of the CATCH program funded by the Dutch Research Council, aims to provide users of ...
Heeren, W., Huijbregts, M., Jong, F. de, Ordelman, R., Werff, L. van der   +4 more
core   +1 more source

How can we detect news surrounding community safety crisis incidents in the internet? Experiments using attention-based Bi-LSTM models

International Journal of Information Management Data Insights
Reports related to community safety crisis incidents are being escalated and shared on social media and other online digital platforms. These reports must be addressed quickly to concerned organizations to provide welfare support to individuals and ...
Yeshanew Ale Wubet, Kuang-Yow Lian
doaj   +1 more source

Automated sign language detection and classification using reptile search algorithm with hybrid deep learning

Heliyon
Sign language recognition (SLR) contains the capability to convert sign language gestures into spoken or written language. This technology is helpful for deaf persons or hard of hearing by providing them with a way to interact with people who do not know
Hadeel Alsolai, Leen Alsolai, Fahd N. Al-Wesabi, Mahmoud Othman, Mohammed Rizwanullah, Amgad Atta Abdelmageed   +5 more
doaj   +1 more source

Developing a negative speech emotion recognition model for safety systems using deep learning

Journal of Big Data
Growing threats in public spaces have forced people to question personal security, making technology more relevant, especially in speech recognition. This paper proposes a security safety system by considering keyword and negative emotion detection to ...
Shreya Jena, Sneha Basak, Himanshi Agrawal, Bunny Saini, Shilpa Gite, Ketan Kotecha, Sultan Alfarhood   +6 more
doaj   +1 more source

Spoken Term Detection Based on Improved Index Structure

Journal of Software, 2013
The performance of keyword spotting system suffers severe degradation when the index stage is so fast that the lattice may lose lots of information to retrieve the spoken terms. In this paper, we focus on this problem and present two algorithm: the first one called unconstraint word graph expansion (UWGE) and the other called dynamic position specific ...
Zhen Zhang, Ji Xu, Yujing Si, Qingwei Zhao, Yonghong Yan   +4 more
openaire   +1 more source

Constructing sub-word units for spoken term detection

, 2017
Spoken term detection, especially of out-of-vocabulary (OOV) keywords, benefits from the use of sub-word systems. We experiment with different language-independent approaches to sub-word unit generation, generating both syllable-like and morpheme-like units, and demonstrate how the performance of syllable-like units can be improved by artificially ...
van Heerden, Charl, Karakos, Damianos, Narasimhan, Karthik, Schwartz, Richard, Davel, Marelie H.   +4 more
openaire   +2 more sources

Spoken Term Detection of Zero-Resource Language Using Posteriorgram of Multiple Languages

Interdisciplinary Information Sciences, 2022
Satoru Mizuochi, Takashi Nose, Akinori Ito   +2 more
semanticscholar   +1 more source