找回密码
 To register

QQ登录

只需一步,快速开始

扫一扫,访问微社区

Titlebook: Statistical Language and Speech Processing; 4th International Co Pavel Král,Carlos Martín-Vide Conference proceedings 2016 Springer Interna

[复制链接]
楼主: inroad
发表于 2025-3-26 21:35:59 | 显示全部楼层
Articulatory Gesture Rich Representation Learning of Phonological Units in Low Resource Settingslower dimensional manifold embedded richly inside the higher-dimensional spectral features like MFCC and PLP. Linguistic or phonetic units of speech can be broken down to a legal inventory of articulatory gestures shared across several phonemes based on their manner of articulation. We intend to dis
发表于 2025-3-27 02:27:13 | 显示全部楼层
Estimating the Severity of Parkinson’s Disease Using Voiced Ratio and Nonlinear Parameterstween acoustic features and the UPDRS severity. The applied acoustic features were the followings: voicing ratio (VR), nonlinear recurrence: the normalized recurrence probability density entropy (.) and fractal scaling: the scaling exponent (.). High diversity is found according to the type of speec
发表于 2025-3-27 05:38:08 | 显示全部楼层
Optimal Feature Set and Minimal Training Size for Pronunciation Adaptation in TTSe, the TTS quality drops when phoneme sequences generated by this converter are inconsistent with those labeled in the speech corpus on which the TTS system is built, or when a given expressivity is desired. To solve this problem, the present work aims at automatically adapting generated pronunciati
发表于 2025-3-27 11:15:58 | 显示全部楼层
发表于 2025-3-27 16:10:50 | 显示全部楼层
Class n-Gram Models for Very Large Vocabulary Speech Recognition of Finnish and Estonianeral millions of words using automatically derived classes. To evaluate the models on Finnish and an Estonian broadcast news speech recognition task, we modify Aalto University’s LVCSR decoder to operate with the class n-grams and very large vocabularies. Linear interpolation of a standard n-gram mo
发表于 2025-3-27 20:26:21 | 显示全部楼层
Combining Syntactic and Acoustic Features for Prosodic Boundary Detection in Russianing the two groups of features yields the efficiency of 0.90, recall of 0.85 and precision of 0.99. It preserves the high recall provided by textual information and the high precision achieved using acoustic information. This is the best published result for Russian.
发表于 2025-3-27 22:12:02 | 显示全部楼层
发表于 2025-3-28 02:52:55 | 显示全部楼层
发表于 2025-3-28 09:31:12 | 显示全部楼层
发表于 2025-3-28 11:04:06 | 显示全部楼层
Delexicalized and Minimally Supervised Parsing on Universal Dependenciesage attachment score of our parser is slightly lower then the delexicalized transfer parser, however, it performs better for languages from less resourced language families (non-Indo-European) and is therefore suitable for those, for which the treebanks often do not exist.
 关于派博传思  派博传思旗下网站  友情链接
派博传思介绍 公司地理位置 论文服务流程 影响因子官网 SITEMAP 大讲堂 北京大学 Oxford Uni. Harvard Uni.
发展历史沿革 期刊点评 投稿经验总结 SCIENCEGARD IMPACTFACTOR 派博系数 清华大学 Yale Uni. Stanford Uni.
|Archiver|手机版|小黑屋| 派博传思国际 ( 京公网安备110108008328) GMT+8, 2025-5-1 19:39
Copyright © 2001-2015 派博传思   京公网安备110108008328 版权所有 All rights reserved
快速回复 返回顶部 返回列表