Progresses in continuous speech recognition based on statistical modelling for Romanian language

被引：0

作者：

Dumitru, Corneliu Octavian ^{[1
]}

Gavat, Inge ^{[1
]}

Militaru, Diana ^{[1
]}

机构：

[1] Univ Politehn Bucuresti, Fac Elect Telecommun & Informat Technol, Bucharest, Romania

来源：

ICINCO 2007: PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL SPSMC: SIGNAL PROCESSING, SYSTEMS MODELING AND CONTROL | 2007年

关键词：

MFCC; LPC; PLP; statistical modelling; monophone; triphone;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we will present progresses made in Automatic Speech Recognition (ASR) for Romanian language based on statistical modelling with hidden Markov models (HMMs). The progresses concern enhancement of modelling by taking into account the context in form of triphones, improvement of speaker independence by applying a gender specific training and enlargement of the feature categories used to describe speech sequences derived not only from perceptual cepstral analysis but also from perceptual linear prediction.

引用

页码：262 / 267

页数：6

共 9 条

[1] [Anonymous], 1992, P ICASSP
[2] Dumitru CO, 2005, Eurocon 2005: The International Conference on Computer as a Tool, Vol 1 and 2 , Proceedings, P1425
[3] GAVAT I, 2000, ELEMENTE SINTEZA REC
[4] GAVAZZI IG, 2003, PERCORSI METACOGNITI, P115
[5] PERCEPTUAL LINEAR PREDICTIVE (PLP) ANALYSIS OF SPEECH
HERMANSKY, H
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1990, 87 (04) : 1738 - 1752
[6] LUPU E, 2004, PRELUCRAREA NUMERICA
[7] OANCEA E, 2004, P COMMUNICATION 2004, P221
[8] WOODLAND PC, 1994, P ICASSP 1994 AD
[9] YOUNG SJ, 1994, ARPA WORKSH HUM LANG

← 1 →