Zobrazeno 1 - 10
of 534
pro vyhledávání: '"Li, Mohan"'
Zero-shot spoken language understanding (SLU) enables systems to comprehend user utterances in new domains without prior exposure to training data. Recent studies often rely on large language models (LLMs), leading to excessive footprints and complex
Externí odkaz:
http://arxiv.org/abs/2406.15209
Multimodal learning has advanced the performance for many vision-language tasks. However, most existing works in embodied dialog research focus on navigation and leave the localization task understudied. The few existing dialog-based localization app
Externí odkaz:
http://arxiv.org/abs/2403.06846
When analyzing the components influencing the stock prices, it is commonly believed that economic activities play an important role. More specifically, asset prices are more sensitive to the systematic economic news that impose a pervasive effect on
Externí odkaz:
http://arxiv.org/abs/2401.04132
This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, latency was optimised by truncating the online attention weights based on t
Externí odkaz:
http://arxiv.org/abs/2304.11985
Autor:
Li, Mohan, Doddipatla, Rama
This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist temporal cla
Externí odkaz:
http://arxiv.org/abs/2304.10869
Publikováno v:
Xiehe Yixue Zazhi, Vol 15, Iss 2, Pp 251-257 (2024)
Pain management, listed as the fifth vital sign, has gained increasing attention from clinicians. Conventional analgesics have limited duration, leading to intense monitor and frequent dosing during the early phase in order to prevent the progression
Externí odkaz:
https://doaj.org/article/add4480ce8af46ce9d2b9b660f73ea8a
This paper proposes a new approach to perform unsupervised fine-tuning and self-training using unlabeled speech data for recurrent neural network (RNN)-Transducer (RNN-T) end-to-end (E2E) automatic speech recognition (ASR) systems. Conventional syste
Externí odkaz:
http://arxiv.org/abs/2207.14736
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous decoder-end adapti
Externí odkaz:
http://arxiv.org/abs/2203.05736
Autor:
Li, Yuanqiao, Li, Qinhong, Li, Mohan, Geng, Fang, Wang, Qingling, Gan, Na, Li, Shugang, Wu, Di
Publikováno v:
In Journal of Molecular Liquids 1 August 2024 407
Publikováno v:
In Biomedical Signal Processing and Control July 2024 93