Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Ram, Dhananjay"'
Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of joint training makes the optimization procedure extremely challenging.
Externí odkaz:
http://arxiv.org/abs/2406.15570
Autor:
Fan, Haozheng, Zhou, Hao, Huang, Guangtai, Raman, Parameswaran, Fu, Xinwei, Gupta, Gaurav, Ram, Dhananjay, Wang, Yida, Huan, Jun
Getting large language models (LLMs) to perform well on the downstream tasks requires pre-training over trillions of tokens. This typically demands a large number of powerful computational devices in addition to a stable distributed training framewor
Externí odkaz:
http://arxiv.org/abs/2404.10630
Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However, the (full)
Externí odkaz:
http://arxiv.org/abs/2310.12442
This paper focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State-of-the-art approaches primarily rely on dynamic time warping (DTW) based template matching techniques using phone posterior or bott
Externí odkaz:
http://arxiv.org/abs/1911.08332
State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching. Here, we present a study o
Externí odkaz:
http://arxiv.org/abs/1907.00443
Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is integrated in the
Externí odkaz:
http://arxiv.org/abs/1809.01576
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each time-step pre
Externí odkaz:
http://arxiv.org/abs/1709.04849
In this work, a Bayesian approach to speaker normalization is proposed to compensate for the degradation in performance of a speaker independent speech recognition system. The speaker normalization method proposed herein uses the technique of vocal t
Externí odkaz:
http://arxiv.org/abs/1610.05948
Publikováno v:
In Speech Communication October 2018 103:27-36
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.