深度循环神经网络在语音识别中的突破
需积分: 49 54 浏览量
更新于2024-09-07
1
收藏 413KB PDF 举报
"这篇学术论文探讨了使用深度循环神经网络（Deep Recurrent Neural Networks, DRNNs）在语音识别中的应用。尽管循环神经网络（RNNs）在处理序列数据时表现出强大的能力，特别是在无输入输出对齐信息的连接主义时间分类（Connectionist Temporal Classification, CTC）任务中，但在语音识别领域，它们的表现一直不如深度前馈网络。作者Alex Graves、Abdel-rahman Mohamed和Geoffrey Hinton通过研究发现，将多层表示与长短期记忆（LSTM）RNN架构相结合的深RNN可以显著提高性能。经过端到端训练并配合适当的正则化，他们展示了深度LSTM RNN在TIMIT音素识别基准测试中达到了17.7%的错误率，这是已知的最佳记录成绩。"
在语音识别中，循环神经网络（RNNs）的使用通常受到其处理长期依赖问题的限制。标准RNN在处理长序列时可能会遇到“梯度消失”或“梯度爆炸”的问题，这使得它们难以捕获远距离的上下文信息。然而，长短期记忆（LSTM）网络通过引入门控机制，有效解决了这个问题，使得它们能够在更长时间尺度上保持和利用信息。
本文的重点是深入研究深度循环神经网络，即将多层结构应用于RNNs，这种结构已经在深度学习中证明了其在特征提取方面的有效性。深度网络允许模型学习不同层次的抽象特征，每一层专注于捕捉不同复杂性的模式。通过结合这些层次的表示与LSTM的能力，DRNNs能够更好地理解语音信号中的时间依赖性，并且在序列标注任务中展现出色的性能。
实验部分，研究者使用端到端训练方法，这是一种无需预先定义输入和输出对齐的训练策略，特别适用于像语音识别这样的时间序列问题。端到端训练使模型能够直接从原始音频信号中学习到音素的表示，而无需依赖于手工设计的声学特征。此外，正则化技术被用于防止过拟合，确保模型在未见过的数据上也能有良好的泛化能力。
在TIMIT音素识别基准测试中，深度LSTM RNN取得了17.7%的测试集错误率，这一成绩表明DRNNs在语音识别领域具有巨大的潜力，超越了之前使用传统RNN和深度前馈网络所取得的结果。这一突破性进展对于语音识别技术的发展具有重要意义，可能推动未来语音识别系统在准确性和效率上的提升。
SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
Alex Graves, Abdel-rahman Mohamed and Geoffrey Hinton
Department of Computer Science, University of Toronto
ABSTRACT
Recurrent neural networks (RNNs) are a powerful model for
sequential data. End-to-end training methods such as Connec-
tionist Temporal Classification make it possible to train RNNs
for sequence labelling problems where the input-output align-
ment is unknown. The combination of these methods with
the Long Short-term Memory RNN architecture has proved
particularly fruitful, delivering state-of-the-art results in cur-
sive handwriting recognition. However RNN performance in
speech recognition has so far been disappointing, with better
results returned by deep feedforward networks. This paper in-
vestigates deep recurrent neural networks, which combine the
multiple levels of representation that have proved so effective
in deep networks with the flexible use of long range context
that empowers RNNs. When trained end-to-end with suit-
able regularisation, we find that deep Long Short-term Mem-
ory RNNs achieve a test set error of 17.7% on the TIMIT
phoneme recognition benchmark, which to our knowledge is
the best recorded score.
Index Terms— recurrent neural networks, deep neural
networks, speech recognition
1. INTRODUCTION
Neural networks have a long history in speech recognition,
usually in combination with hidden Markov models [1, 2].
They have gained attention in recent years with the dramatic
improvements in acoustic modelling yielded by deep feed-
forward networks [3, 4]. Given that speech is an inherently
dynamic process, it seems natural to consider recurrent neu-
ral networks (RNNs) as an alternative model. HMM-RNN
systems [5] have also seen a recent revival [6, 7], but do not
currently perform as well as deep networks.
Instead of combining RNNs with HMMs, it is possible
to train RNNs ‘end-to-end’ for speech recognition [8, 9, 10].
This approach exploits the larger state-space and richer dy-
namics of RNNs compared to HMMs, and avoids the prob-
lem of using potentially incorrect alignments as training tar-
gets. The combination of Long Short-term Memory [11], an
RNN architecture with an improved memory, with end-to-end
training has proved especially effective for cursive handwrit-
ing recognition [12, 13]. However it has so far made little
impact on speech recognition.
RNNs are inherently deep in time, since their hidden state
is a function of all previous hidden states. The question that
inspired this paper was whether RNNs could also benefit from
depth in space; that is from stacking multiple recurrent hid-
den layers on top of each other, just as feedforward layers are
stacked in conventional deep networks. To answer this ques-
tion we introduce deep Long Short-term Memory RNNs and
assess their potential for speech recognition. We also present
an enhancement to a recently introduced end-to-end learning
method that jointly trains two separate RNNs as acoustic and
linguistic models [10]. Sections 2 and 3 describe the network
architectures and training methods, Section 4 provides exper-
imental results and concluding remarks are given in Section 5.
2. RECURRENT NEURAL NETWORKS
Given an input sequence x = (x
1
, . . . , x
T
), a standard recur-
rent neural network (RNN) computes the hidden vector se-
quence h = (h
1
, . . . , h
T
) and output vector sequence y =
(y
1
, . . . , y
T
) by iterating the following equations from t = 1
to T :
h
t
= H (W
xh
x
t
+ W
hh
h
t−1
+ b
h
) (1)
y
t
= W
hy
h
t
+ b
y
(2)
where the W terms denote weight matrices (e.g. W
xh
is the
input-hidden weight matrix), the b terms denote bias vectors
(e.g. b
h
is hidden bias vector) and H is the hidden layer func-
tion.
H is usually an elementwise application of a sigmoid
function. However we have found that the Long Short-Term
Memory (LSTM) architecture [11], which uses purpose-built
memory cells to store information, is better at finding and ex-
ploiting long range context. Fig. 1 illustrates a single LSTM
memory cell. For the version of LSTM used in this paper [14]
H is implemented by the following composite function:
i
t
= σ (W
xi
x
t
+ W
hi
h
t−1
+ W
ci
c
t−1
+ b
i
) (3)
f
t
= σ (W
xf
x
t
+ W
hf
h
t−1
+ W
cf
c
t−1
+ b
f
) (4)
c
t
= f
t
c
t−1
+ i
t
tanh (W
xc
x
t
+ W
hc
h
t−1
+ b
c
) (5)
o
t
= σ (W
xo
x
t
+ W
ho
h
t−1
+ W
co
c
t
+ b
o
) (6)
h
t
= o
t
tanh(c
t
) (7)
where σ is the logistic sigmoid function, and i, f, o and c
are respectively the input gate, forget gate, output gate and
arXiv:1303.5778v1 [cs.NE] 22 Mar 2013
下载后可阅读完整内容，剩余4页未读，立即下载
2019-08-26 上传
2020-02-27 上传
2014-03-09 上传
点击了解资源详情
2009-04-25 上传
2019-08-26 上传
2017-11-07 上传
2023-08-23 上传
xinghaoyan
- 粉丝: 11
- 资源: 79
我的内容管理
展开
最新资源
- JavaScript实现的高效pomodoro时钟教程
- CMake 3.25.3版本发布：程序员必备构建工具
- 直流无刷电机控制技术项目源码集合
- Ak Kamal电子安全客户端加载器-CRX插件介绍
- 揭露流氓软件：月息背后的秘密
- 京东自动抢购茅台脚本指南：如何设置eid与fp参数
- 动态格式化Matlab轴刻度标签 - ticklabelformat实用教程
- DSTUHack2021后端接口与Go语言实现解析
- CMake 3.25.2版本Linux软件包发布
- Node.js网络数据抓取技术深入解析
- QRSorteios-crx扩展：优化税务文件扫描流程
- 掌握JavaScript中的算法技巧
- Rails+React打造MF员工租房解决方案
- Utsanjan：自学成才的UI/UX设计师与技术博客作者
- CMake 3.25.2版本发布，支持Windows x86_64架构
- AR_RENTAL平台：HTML技术在增强现实领域的应用
