26 Hits in 6.1 sec

Fuzzy-based discriminative feature representation for children's speech recognition

Seyed Mostafa Mirhassani, Hua-Nong Ting
2014 Digital signal processing (Print)  
Upon extracting the features, two well-known classification methods, namely, MLP and HMM, were employed for the speech recognition task.  ...  topic in computer-based speech recognition systems.  ...  Acknowledgments The authors would like to thank the University of Malaya for funding this study under UMRG grant (RP016A-13AET).  ... 
doi:10.1016/j.dsp.2014.05.004 fatcat:3njklbg4zfh2fmntq3cb7jul5q

Hybrid PSO-ANFIS for Speaker Recognition

Samiya Silarbi, Redouane Tlemsani, Abderrahmane Bendahmane
2021 International Journal of Cognitive Informatics and Natural Intelligence  
The hybrid PSO-ANFIS model is performed for speaker recognition on CHAINS speech dataset.  ...  This paper introduces an evolutionary approach for training the adaptive network-based fuzzy inference system (ANFIS).  ...  Only ANFIS: Hybrid learning that combines GD and LSE is used, MATLAB reference function (Fuzzy Logic Toolbox, 2000) Hybrid PSO-ANFIS The optimum PSO parameters can be determined based on several parametric  ... 
doi:10.4018/ijcini.20210401.oa7 fatcat:3d2adubxmfboxodebemdq3tzeu

Natural Language Processing based Soft Computing Techniques

Jabar H.Yousif
2013 International Journal of Computer Applications  
The part of speech taggers (POS) is the process of categorization words based on their meaning, functions and types (noun, verb, adjective, etc).  ...  Two stages tagging system based MPL, FRNN and SVM are implemented and designed. The system helps to classify words and assign the correct POS for each of them.  ...  , 22, 23 and 26] or the hybrid systems [8] .  ... 
doi:10.5120/13418-1089 fatcat:fwgfpeoa6jezflnpmnxa6cvlpm

A neurocomputing framework: From methodologies to application

Sung-Bae Cho
1996 Neurocomputing  
For learning we present a rapid learning method based on Aitken's A2 process and a training schedule called selective reinforcement learning; for architecture, a two-stage classification scheme and a multiple  ...  In order to investigate the behavior of neural network classifiers with the proposed methodologies, we designed and implemented neuml networks for recognizing on-line handwriting characters obtained by  ...  Kim of the Department of Computer Science at KAIST for continuous encouragement.  ... 
doi:10.1016/0925-2312(95)00089-5 fatcat:vrar272atvfw7jkmfvwb7uk7vm

Cultural dependency analysis for understanding speech emotion

Norhaslinda Kamaruddin, Abdul Wahab, Chai Quek
2012 Expert systems with applications  
Understanding culture dependency is thus important to the performance of the speech emotion recognition system.  ...  Features were extracted using Mel Frequency Cepstral Co-efficient (MFCC) method and classified with neural network (Multi Layer Perceptron (MLP)) and fuzzy neural networks; namely: Adaptive Network Fuzzy  ...  Adaptive Network-based Fuzzy Inference System (ANFIS) Adaptive Network-based Fuzzy Inference System (ANFIS) Jang, 1993 was adopted as one of the fuzzy neural network classifiers to compare the different  ... 
doi:10.1016/j.eswa.2011.11.028 fatcat:2msreer7rzhsnk3j6cz2fxqxf4

Recent Advancement in Speech Recognition for Bangla: A Survey

Sadia Sultana, M. Shahidur, M. Zafar
2021 International Journal of Advanced Computer Science and Applications  
This paper presents a brief study of remarkable works done for the development of Automatic Speech Recognition (ASR) system for Bangla language.  ...  Different studies carried out on last decade for Bangla speech recognition have been shortly reviewed in a chronological order.  ...  For unsupervised systems there are no example patterns, these systems are learn-based. Recent researches focus on speech recognition based on DNN, RNN, hybrid of HMM-DNN approaches. E.  ... 
doi:10.14569/ijacsa.2021.0120365 fatcat:5cdsy57zyjhvlitr5wfcqvie3e

Systematic Literature Review of Dialectal Arabic: Identification and Detection

Ashraf Elnagar, Sane Yagi, Ali Bou Nassif, Ismail Shahin, Said A. Salloum
2021 IEEE Access  
, a hybrid statistical and rule-based system to translate them into English.  ...  ( A hybrid of PSO and fuzzy logic) n-gram Egyptian Article Egyptian Computer Science Journal A9 [123] 2015 Speech Corpus BR (Speech) News and Media N/A N/A N/A Egyptian, Levantine  ...  For more information, see This article has been accepted for publication in a future issue of this journal, but has not been fully edited.  ... 
doi:10.1109/access.2021.3059504 fatcat:d7dkxmdehzcq5d7fej7icyy6rq

A survey on optical character recognition for Bangla and Devanagari scripts

2013 Sadhana (Bangalore)  
The past few decades have witnessed an intensive research on optical character recognition (OCR) for Roman, Chinese, and Japanese scripts.  ...  A lot of work has been also reported on OCR efforts for various Indian scripts, like Devanagari, Bangla, Oriya, Tamil, Telugu, Malayalam, Kannada, Gurmukhi, Gujarati, etc.  ...  Bhowmik et al (2004) have introduced a recognition method using MLP classifier based on stroke features.  ... 
doi:10.1007/s12046-013-0121-9 fatcat:4fna65koxfhw7hwehsrjhe34ma

Development of Part of Speech Tagger using Deep Learning

2019 International Journal of Engineering and Advanced Technology  
In this research project part of speech tagging is perform on Hindi. Hindi is the fourth most popular language and spoken by approximately 4billion people across the globe.  ...  Part of speech tagging is the initial step in development of NLP (natural language processing) application.  ...  Dandapat [4] developed a hybrid tagging model, the training model is based on partially supervised learning, for supervised and unsupervised learning HMM is used.  ... 
doi:10.35940/ijeat.a1531.109119 fatcat:d2n3vj47hzbqlb2soll43t7mxy

A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances [article]

Yan Wang, Wei Song, Wei Tao, Antonio Liotta, Dawei Yang, Xinlei Li, Shuyong Gao, Yixuan Sun, Weifeng Ge, Wei Zhang, Wenqiang Zhang
2022 arXiv   pre-print
Physical-based affect recognition caters to more researchers due to multiple public databases.  ...  Instead of focusing on one specific field of affective analysis, we systematically review recent advances in the affective computing, and taxonomize unimodal affect recognition as well as multimodal affective  ...  The change of key features in AAM and a fuzzy logic model is utilized to recognize facial expression based on prior knowledge derived from FACS [238] .  ... 
arXiv:2203.06935v3 fatcat:h4t3omkzjvcejn2kpvxns7n2qe

Visual Words for Automatic Lip-Reading [article]

Ahmad Basheer Hassanat
2014 arXiv   pre-print
Indeed, automating the human ability to lip read, a process referred to as visual speech recognition, could open the door for other novel applications.  ...  This thesis investigates various issues faced by an automated lip-reading system and proposes a novel "visual words" based approach to automatic lip reading.  ...  HMM for visual speech recognition Most visual speech recognition systems in the literature use HMM for both visemes classification and word recognition.  ... 
arXiv:1409.6689v1 fatcat:j2qt74bs7ngdrguwz7v4e6ktla

Deep Learning for Distant Speech Recognition [article]

Mirco Ravanelli
2017 arXiv   pre-print
The latter disturbances severely hamper the intelligibility of a speech signal, making Distant Speech Recognition (DSR) one of the major open challenges in the field.  ...  We then investigate on approaches for better exploiting speech contexts, proposing some original methodologies for both feed-forward and recurrent neural networks.  ...  DNN-HMM speech recognizers are often called hybrid systems, since they are based on both a generative (HMM) and a discriminative (DNN) model, offering a significant performance gain over GMM-HMM solutions  ... 
arXiv:1712.06086v1 fatcat:2b7ymqmihjan5nkxeqrxq52wki

Language and variety verification on broadcast news for Portuguese

Jean-Luc Rouas, Isabel Trancoso, Céu Viana, Mónica Abreu
2008 Speech Communication  
The two-stage system is designed to be used as a pre-processing module for the Portuguese Automatic Speech Recognition (ASR) system developed at INESC-ID.  ...  The identification results are then used either to mark the speech data as untranscribable or forward it to the European Portuguese ASR system, or a system tuned for other languages or varieties.  ...  The authors would like to thank our colleagues Hugo Meinedo and Ernesto de Andrade for helpful comments.  ... 
doi:10.1016/j.specom.2008.05.006 fatcat:227n3l7sgndhnkiweewkiycdii

The EVALITA Dependency Parsing Task: From 2007 to 2011 [chapter]

Cristina Bosco, Alessandro Mazzei
2013 Lecture Notes in Computer Science  
results of 8 tasks, 4 of which focusing on written language and 4 on speech technologies.  ...  Established in 2007, EVALITA ( is the evaluation campaign of Natural Language Processing and Speech Technologies for the Italian language, organized around shared tasks focusing on  ...  Acknowledgements This work is partially funded by the ATS Romantic Living Lab under the Apulian ICT Living Labs program and the project PON 01 00850 ASK-Health (Advanced System for the interpretation and  ... 
doi:10.1007/978-3-642-35828-9_1 fatcat:p6dyjaxm4zbitfajtciwclwipu

Over a Decade of Social Opinion Mining [article]

Keith Cortis, Brian Davis
2020 arXiv   pre-print
Social media popularity and importance is on the increase, due to people using it for various types of social interaction across multiple channels.  ...  These can be utilised in many application areas, ranging from marketing, advertising and sales for product/service management, and in multiple domains and industries, such as politics, technology, finance  ...  [313] present a sentiment evaluation and analysis system based on fuzzy linguistic textual analysis.  ... 
arXiv:2012.03091v1 fatcat:bm5nydbdvbalzi33l3w2ivkdja
« Previous Showing results 1 — 15 out of 26 results