.png){kind=icon}
返回
Algorithms for data-driven ASR parameter quantization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2005.10.003.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
There is fast growing research on designing energy-efficient computational devices and applications running on them. As one of the most compelling applications for mobile devices, automatic speech recognition (ASR) requires new methods to allow it to use fewer computational. and memory resources while still achieving a high level of accuracy. One way to achieve this is through parameter quantization. In this work, we compare a variety of novel. sub-vector clustering procedures for ASR system parameter quantization. Specifically, we look at systematic data-driven sub-vector selection techniques, most of which Are based on entropy minimization, and others on recognition accuracy maximization on a development set. We compare performance on two speech databases, PHONEBOOK, an isolated word speech recognition task, and TIMIT, a phonetically diverse connected-word speech corpus. While the optimal entropy-minimizing or accuracy-driven quantization methods are intractable, several simple schemes including scalar quantization with separate codebooks per parameter and joint scalar quantization with normalization perform well in their attempt to approximate the optimal clustering. (c) 2005 Elsevier Ltd. All rights reserved.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
3.4
论文数:
1.5K
被引数:
2.6K
机构
暂无机构信息
引用论文
Near Surface Mounted Composites for Flexural Strengthening of Reinforced Concrete Beams.png)
Polymers
OAAI
PolymersIF0
OAAI分享收藏Synthèse, Par la Méthode de Hewett, Des Benzo [a]Naphto[2,1‐j]Anthracéne, Naphto[2,1‐c]Chrysene, Benzo[a]Picéne et 8,16‐Diméthoxycarbonylbenzo[c] Naphto [2,1‐1] Chrysene合成，通过Hewett方法，苯并[a]萘并[2,1‐j]蒽，萘并[2,1‐c]屈，苯并[a]蒽并[2,1‐j]屈和8,16‐二甲氧羰基苯并[c]萘并[2,1‐l]屈
PREAI
分享收藏
A critical re-evaluation of monocotyledons as described by Weyland and co-authors from the Rhenish browncoal (Miocene, Germany)对Weyland及其合作者根据德国莱茵褐煤层（中新世）描述的单子叶植物进行的批判性重新评估
PREAI
分享收藏
查看更多内容