Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Hwang, Kyuyeon"'
Autor:
Hwang, Kyuyeon1 (AUTHOR) kyuyeonhwang@ruc.edu.cn, Han, Junhee2 (AUTHOR)
Publikováno v:
Economies. Nov2024, Vol. 12 Issue 11, p303. 18p.
Autor:
Hu, Ting-Yao, Shrivastava, Ashish, Chang, Jen-Hao Rick, Koppula, Hema, Braun, Stefan, Hwang, Kyuyeon, Kalinli, Ozlem, Tuzel, Oncel
Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all samples. W
Externí odkaz:
http://arxiv.org/abs/2011.01156
The complexity of deep neural network algorithms for hardware implementation can be lowered either by scaling the number of units or reducing the word-length of weights. Both approaches, however, can accompany the performance degradation although man
Externí odkaz:
http://arxiv.org/abs/1611.06342
In this paper, a neural network based real-time speech recognition (SR) system is developed using an FPGA for very low-power operation. The implemented system employs two recurrent neural networks (RNNs); one is a speech-to-character RNN for acoustic
Externí odkaz:
http://arxiv.org/abs/1610.00552
Autor:
Hwang, Kyuyeon, Sung, Wonyong
Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs
Externí odkaz:
http://arxiv.org/abs/1609.03777
In this paper, we propose a generative knowledge transfer technique that trains an RNN based language model (student network) using text and output probabilities generated from a previously trained RNN (teacher network). The text generation can be co
Externí odkaz:
http://arxiv.org/abs/1608.04077
Autor:
Hwang, Kyuyeon, Sung, Wonyong
In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are gradually improved
Externí odkaz:
http://arxiv.org/abs/1601.06581
In this paper, we propose a context-aware keyword spotting model employing a character-level recurrent neural network (RNN) for spoken term detection in continuous speech. The RNN is end-to-end trained with connectionist temporal classification (CTC)
Externí odkaz:
http://arxiv.org/abs/1512.08903
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network c
Externí odkaz:
http://arxiv.org/abs/1512.08571
Recurrent neural networks have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardware complexity can be much lowered by minimizing the word-length of wei
Externí odkaz:
http://arxiv.org/abs/1512.01322