Zobrazeno 1 - 10
of 7 181
pro vyhledávání: '"Hira, P"'
Active learning aims to reduce the required number of labeled data for machine learning algorithms by selectively querying the labels of initially unlabeled data points. Ensuring the replicability of results, where an algorithm consistently produces
Externí odkaz:
http://arxiv.org/abs/2412.09686
Understanding future weather changes at regional and local scales is crucial for planning and decision-making, particularly in the context of extreme weather events, as well as for broader applications in agriculture, insurance, and infrastructure de
Externí odkaz:
http://arxiv.org/abs/2411.14774
Climate models serve as critical tools for evaluating the effects of climate change and projecting future climate scenarios. However, the reliance on numerical simulations of physical equations renders them computationally intensive and inefficient.
Externí odkaz:
http://arxiv.org/abs/2410.21657
Autor:
Dhamyal, Hira, Singh, Rita
The quality of human voice plays an important role across various fields like music, speech therapy, and communication, yet it lacks a universally accepted, objective definition. Instead, voice quality is referred to using subjective descriptors like
Externí odkaz:
http://arxiv.org/abs/2410.09578
Speaker verification systems are crucial for authenticating identity through voice. Traditionally, these systems focus on comparing feature vectors, overlooking the speech's content. However, this paper challenges this by highlighting the importance
Externí odkaz:
http://arxiv.org/abs/2409.05799
Autor:
Waseem, Hira, Hafeez, Abdul
The decays governed by the flavor-changing-neutral-current transitions (FCNC), such as $b\to s\ell^{+}\ell^{-}$, provide an important tool to test the physics in and beyond the Standard Model (SM). This work focuses on investigating the FCNC process
Externí odkaz:
http://arxiv.org/abs/2408.17436
Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of the recording. In this paper, we examine whether summaries based on anno
Externí odkaz:
http://arxiv.org/abs/2408.07277
Speech Emotion Recognition (SER) has been traditionally formulated as a classification task. However, emotions are generally a spectrum whose distribution varies from situation to situation leading to poor Out-of-Domain (OOD) performance. We take ins
Externí odkaz:
http://arxiv.org/abs/2407.15300
Autor:
Asif, Hira, Sahin, Ramazan
Electro-optic control of quantum dots embedded in the plasmonic nanocavities enables active tuning of photonic devices for emerging applications in Quantum optics such as quantum information processing, entanglement and ultrafast optical switching. H
Externí odkaz:
http://arxiv.org/abs/2406.19173
Autor:
Arora, Siddhant, Pasad, Ankita, Chien, Chung-Ming, Han, Jionghao, Sharma, Roshan, Jung, Jee-weon, Dhamyal, Hira, Chen, William, Shon, Suwon, Lee, Hung-yi, Livescu, Karen, Watanabe, Shinji
The Spoken Language Understanding Evaluation (SLUE) suite of benchmark tasks was recently introduced to address the need for open resources and benchmarking of complex spoken language understanding (SLU) tasks, including both classification and seque
Externí odkaz:
http://arxiv.org/abs/2406.10083