265,608 Hits in 5.4 sec

A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data

Priya Rani, Shardul Suryawanshi, Koustava Goswami, Bharathi Raja Chakravarthi, Theodorus Fransen, John Philip McCrae
2020 Zenodo  
In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text.  ...  In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora.  ...  A Hindi-English code-mixed data set was created to study the problem of hate speech detection in such data.  ... 
doi:10.5281/zenodo.3842627 fatcat:q3ysbwosnfhftmniko7dlf2aiy

Improving Accuracy of Isolated Word Recognition System by using Syllable Number Characteristics

Risanuri Hidayat, Anggun Winursito
2020 International Journal of Technology  
The addition of syllable detection algorithms in version three increased the computational time by only 0.151 s compared to the conventional MFCC method.  ...  First, the syllable number of speech signals to be recognized was detected, and then, the detection results were used to call one of the database groups that matched the syllable number characteristics  ...  The addition of syllable detection algorithms to version three of the proposed method only increased the computation time by 0.151 s compared with the conventional MFCC method.  ... 
doi:10.14716/ijtech.v11i2.3678 doaj:38ca10556a8947b98165a7a30a33a7ed fatcat:trofpfqfpjcobhyiz4i5t5evfu

Vowel onset point detection for noisy speech using spectral energy at formant frequencies

Anil Kumar Vuppala, K. Sreenivasa Rao
2012 International Journal of Speech Technology  
In this paper, we propose a method for robust detection of the vowel onset points (VOPs) from noisy speech.  ...  Significant improvement in the performance of VOP detection is observed by using proposed method compared to existing method.  ...  Performance of the proposed VOP detection method for noisy speech is compared with COMB-ESM method. Table 1 shows the performance of VOP detection methods on TIMIT database under noise.  ... 
doi:10.1007/s10772-012-9179-8 fatcat:2imhznyudbgfvpiz6454sncdoi

Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Detection

Subba Ramaiah V, Rajeswara Rao R
2016 International Journal on Cybernetics & Informatics  
Multi-Speaker activity (MSA) detection helps in detecting the presence of whether the speech signals has a single speaker or multiple speaker speeches in the speech signal.  ...  It is easy to calculate the slope at ZCs (zero crossings) of the speech signal and makes a comparison with a suitable threshold (Th).  ...  Recently in [18] , the authors have approached a method based on the measurement of the ZCR. A comparison has been done for DT detection.  ... 
doi:10.5121/ijci.2016.5415 fatcat:fpsnffgzdnaorpqgkv4hzbbw64

A Deep Learning Based Method for Parkinson's Disease Detection Using Dynamic Features of Speech

Changqin Quan, Kang Ren, Zhiwei Luo
2021 IEEE Access  
This study explores static and dynamic speech features relating to PD detection.  ...  A comparative analysis of the articulation transition characteristics shows that the number of articulation transitions and the trend of the fundamental frequency curve are significantly different between  ...  In the task of PD detection from speech, the performance of a ML based method is mainly affected by the speech features and the architecture of ML models.  ... 
doi:10.1109/access.2021.3051432 fatcat:ytz3va7tqzf5bebixi6bek4mwu

An Automatic Prolongation Detection Approach in Continuous Speech With Robustness Against Speaking Rate Variations

Iman Esmaili, NaderJafarnia Dabanloo, Mansour Vali
2017 Journal of Medical Signals & Sensors  
The aim of this study was to develop a method to help speech-language pathologists (SLPs) during diagnosis and treatment sessions.  ...  The proposed method was evaluated by UCLASS and self-recorded Persian speech databases. The results were also compared with three high-performance studies in automatic prolongation detection.  ...  In this study, 12 coefficients of PLP features were employed for automatic detection of prolongation sounds. In this study, we used cross-correlation to check the similarity of speech frames.  ... 
doi:10.4103/2228-7477.199156 fatcat:o33so4dn6baxnch4adzdwsuq34

Application of Preemphasis FIR Filtering To Speech Detection and Phoneme Segmentation
프리엠퍼시스 FIR 필터링의 음성 검출 및 음소 분할에의 응용

Chang-Young Lee
2013 The Journal of the Korea institute of electronic communication sciences  
In this paper, we propose a new method of speech detection and phoneme segmentation.  ...  It is verified experimentally that the silence / speech boundary becomes sharper by applying the filtering compared to the conventional method.  ...  In this paper, we study a method of speech detection that employs finite impulse response (FIR) filter. This method is especially effective in removing the noise of low-frequency regime.  ... 
doi:10.13067/jkiecs.2013.8.5.665 fatcat:jqu2krsvxfghvk6my5sd2acwte

Large Comparative Study of Recent Computational Approach in Automatic Hate Speech Detection

Wesam Shishah, Ricky Maulana Fajri
2022 TEM Journal  
To the author's knowledge, this paper is the first attempt to present a large comparative study of approaches in hate speech detection.  ...  Although many studies are already implemented in detecting hate content, many of these are done in a single setting showing a single dataset in comparison to machine learning or deep learning models.  ...  A Recent study of logistic regression on hate speech detection was performed by Ginting et al., [4] . This study conducted multinomial logistic regression for Indonesian hate speech detection.  ... 
doi:10.18421/tem111-10 fatcat:g4sl3tvsj5fjbavj2xzdd3d3ya

Front-End of Vehicle-Embedded Speech Recognition for Voice-Driven Multi-UAVs Control

Jeong-Sik Park, Hyeong-Ju Na
2020 Applied Sciences  
Although many studies have introduced several systems for voice-driven UAV control, most have focused on a general speech recognition architecture to control a single UAV.  ...  In addition, we propose a multi-channel voice trigger method that can control multiple UAVs while efficiently directing and switching the target vehicle via speech commands.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10196876 fatcat:glp2hql545ajjmum7h53yrhsfy

EEG-based Speech Activity Detection

2021 Acta Polytechnica Hungarica  
EEG data uploaded while pronouncing 50 different phrases were classified using a feed-forward neural network. As a result of detection, a 0.82 F1 score was achieved.  ...  In this article, we propose a speech activity detector algorithm, which, as expected, should improve the performance of the EEG based speech recognition system.  ...  Acknowledgment The research in this paper was supported by the Ministry of Education, Science, Research and Sport of the Slovak Republic under the project KEGA 009TUKE-4/2019 and by the Slovak Research  ... 
doi:10.12700/aph.18.1.2021.1.5 fatcat:yvwfrrgdzzebdndp7i7ogpolra

VOP Detection for Read and Conversation Speech using CWT Coefficients and Phone Boundaries [article]

Kumud Tripathi, K. Sreenivasa Rao
2019 arXiv   pre-print
To address this issue, we proposed a two-stage approach for accurate detection of VOPs.  ...  In this paper, we propose a novel approach for accurate detection of the vowel onset points (VOPs). VOP is the instant at which the vowel begins in the speech signal.  ...  Due to high dissimilarity, it's important to study the impact of both the modes on the vowel onset point (VOP) detection. Vowel onset point represents the start of a vowel in a speech signal.  ... 
arXiv:1908.08668v1 fatcat:55hlcmwx45cptfmf3zrvp5o33m

Machine Learning Approach for Depression Detection in Japanese

Yutaka Miyaji Yuka Niimi
2021 Pacific Asia Conference on Language, Information and Computation  
In this study, to detect depression based on linguistic features, even in documents that do not explicitly mention the topic of depression, we build a machine learning model that detects depression in  ...  However, in Japanese text, there are only two studies that have addressed the detection of depression.  ...  Method The purpose of this study is to detect depression in Japanese.  ... 
dblp:conf/paclic/Niimi21 fatcat:c2vk45zd3zarhpghh554q4pxp4

Spoofing detection goes noisy: An analysis of synthetic speech detection in the presence of additive noise

Cemal Hanilçi, Tomi Kinnunen, Md Sahidullah, Aleksandr Sizov
2016 Speech Communication  
Most of the prior studies on synthesized or converted speech detection report their findings using high-quality clean recordings.  ...  To this end, our study provides a comparative analysis of existing state-of-the-art, off-the-shelf synthetic speech detectors under additive noise contamination with a special focus on front-end processing  ...  A comparative evaluation of a large number of speech features for this task is available in [33] .  ... 
doi:10.1016/j.specom.2016.10.002 fatcat:tubry7mdavci3b7fe2hmumkaqu

Voice activity detection in noise using modulation spectrum of speech: Investigation of speech frequency and modulation frequency ranges

Kimhuoch Pek, Takayuki Arai, Noboru Kanedera
2012 Acoustical Science and Technology  
Voice activity detection (VAD) in noisy environments is a very important preprocessing scheme in speech communication technology, a field which includes speech recognition, speech coding, speech enhancement  ...  In Experiment 2, we use one of the best parameter settings from Experiment 1 and evaluate the real environment data in the CENSREC-1-C corpus by comparing our method with other conventional methods.  ...  ACKNOWLEDGMENT This study work was partially supported by Sophia University Open Research Center from MEXT. The authors would like to thank Junko Yoshii, Fujiyama Inc., for her support.  ... 
doi:10.1250/ast.33.33 fatcat:noarqlottjftlcft5z2f24smgq

Investigation and evaluation of glottal flow waveform for voice pathology detection

Yuanbo Wu, Changwei Zhou, Ziqi Fan, Di Wu, Xiaojun Zhang, Zhi Tao
2020 IEEE Access  
Compared to state-of-the-art methods, the proposed method achieves the highest accuracy for the Massachusetts Eye and Ear Infirmary database and an increase of 2.75-17.16% in detection accuracy compared  ...  In addition, a feature selection method in terms of the wrapper approach is used to combine the single features ranked by using the Fisher discrimination ratio.  ...  Compared to other stateof-the-art detection methods, the proposed method achieved the highest accuracy in the MEEI database and an increase of 2.75-17.16% in detection accuracy compared to other conventional  ... 
doi:10.1109/access.2020.3046767 fatcat:v2mouiw42zharguktxpfisf4wu
« Previous Showing results 1 — 15 out of 265,608 results