Zobrazeno 1 - 10
of 11 963
pro vyhledávání: '"WANG, Quan"'
Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images, thereby enhancing the performance of detectors in complex environments. However, existing methods often neglect the frequency char
Externí odkaz:
http://arxiv.org/abs/2412.09258
Remote sensing change detection aims to perceive changes occurring on the Earth's surface from remote sensing data in different periods, and feed these changes back to humans. However, most existing methods only focus on detecting change regions, lac
Externí odkaz:
http://arxiv.org/abs/2410.23828
We propose GE2E-KWS -- a generalized end-to-end training and evaluation framework for customized keyword spotting. Specifically, enrollment utterances are separated and grouped by keywords from the training batch and their embedding centroids are com
Externí odkaz:
http://arxiv.org/abs/2410.16647
Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc overall improv
Externí odkaz:
http://arxiv.org/abs/2410.00508
Autor:
Ma, Shixuan, Wang, Quan
The increasing capability and widespread usage of large language models (LLMs) highlight the desirability of automatic detection of LLM-generated text. Zero-shot detectors, due to their training-free nature, have received considerable attention and n
Externí odkaz:
http://arxiv.org/abs/2409.16914
Autor:
Park, Hyun Jin, Agarwal, Dhruuv, Chen, Neng, Sun, Rentao, Partridge, Kurt, Chen, Justin, Zhang, Harry, Zhu, Pai, Bartel, Jacob, Kastner, Kyle, Wang, Gary, Rosenberg, Andrew, Wang, Quan
The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speech (TTS) synthesized data can reduce the cost and time associated with
Externí odkaz:
http://arxiv.org/abs/2408.10463
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting effect in life
Externí odkaz:
http://arxiv.org/abs/2408.11869
Autor:
Park, Hyun Jin, Agarwal, Dhruuv, Chen, Neng, Sun, Rentao, Partridge, Kurt, Chen, Justin, Zhang, Harry, Zhu, Pai, Bartel, Jacob, Kastner, Kyle, Wang, Gary, Rosenberg, Andrew, Wang, Quan
This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amount of training data to be accurate, and obtaining such training data c
Externí odkaz:
http://arxiv.org/abs/2407.18879
One of the challenges in developing a high quality custom keyword spotting (KWS) model is the lengthy and expensive process of collecting training data covering a wide range of languages, phrases and speaking styles. We introduce Synth4Kws - a framew
Externí odkaz:
http://arxiv.org/abs/2407.16840
Autor:
Chi, Hanbin, Hu, Yueqiang, Ou, Xiangnian, Jiang, Yuting, Yu, Dian, Lou, Shaozhen, Wang, Quan, Xie, Qiong, Qiu, Cheng-Wei, Duan, Huigao
Flexible control light field across multiple parameters is the cornerstone of versatile and miniaturized optical devices. Metasurfaces, comprising subwavelength scatterers, offer a potent platform for executing such precise manipulations. However, th
Externí odkaz:
http://arxiv.org/abs/2407.00559