“No official publication to date on the speech experiments themselves, but the procedure is well documented in his paper [3]”
Generating Sequences With Recurrent Neural Networks
用 LSTM 逐点预测生成文本,并合成逼真的手写体
论文展示了如何仅通过每次预测一个数据点,用长短期记忆(LSTM)循环神经网络生成具有长程结构的复杂序列,并在文本(离散数据)和在线手写(实值数据)上演示。作者进一步让网络的预测以文本序列为条件,实现手写合成,所得系统能生成各种风格、高度逼真的草书手写体。
HN 上的人把它当作 LSTM 序列生成的早期经典,称它启发了后来大量手写和语音合成工作,并引用其中 RNN 生成维基百科文本等样例,也说其技术可移植到任何现代框架。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Older one, but important to understand deeply since other recent ideas have come from this!”
“Man, the RNN-generated Wikipedia data around page 14 of Generating Sequences With Recurrent Neural Networks is fascinating.”
“But one of the early deep learning papers from Alex Graves does this really well with LSTMs - Generating Sequences With Recurrent Neural Networks”
“handwriting generation [12]”
“Generating Sequences With Recurrent Neural Networks”
看全部 15 条 →
“Other attentions such as [2],[3] are constrained either to only move forward or to be a hybrid of forward movement and (pooled) global lookup.”
“Alex Graves achieved 1.33 bits per character using stacked LSTMs.[1]”
“some of the most impressive deep learning results have been obtained with these.”
“There is an older paper [0] and demo from [1] Alex Graves that inspired a ton of work around handwriting, and then speech.”
“We took the terms from existing works that we knew:”
“work on "Generating Sequences With Recurrent Neural Networks", including his unpublished TTS demo [1].”
“This problem was more or less solved with neural networks in 2013, see Generating Sequences With Recurrent Neural Networks.”
“Looks like it's based on this paper [1].”
“One could also port the techniques described in the paper, Generating Sequences With Recurrent Neural Networks using any modern machine learning framework.”