Filters








115 Hits in 4.5 sec

Development of Acoustical Feature Based Classifier Using Decision Fusion Technique for Malay Language Disfluencies Classification

Raseeda Hamzah, Nursuriati Jamil, Rosniza Roslan
2017 Indonesian Journal of Electrical Engineering and Computer Science  
of Malay language filled pause (FP) and elongation (ELO).  ...  <p>Speech disfluency such as filled pause (FP) is a hindrance in Automated Speech Recognition as it degrades the accuracy performance.  ...  The daily communication type of speech used by human is spontaneous speech that highly contain filled pause.  ... 
doi:10.11591/ijeecs.v8.i1.pp262-267 fatcat:o7ghx5bci5bbjjcz433jwdpyre

INVESTIGATION OF SPEECH DISFLUENCIES CLASSIFICATION ON DIFFERENT THRESHOLD SELECTION TECHNIQUES USING ENERGY FEATURE EXTRACTION

Raseeda Hamzah, Nursuriati Jamil
2019 MALAYSIAN JOURNAL OF COMPUTING  
Various samples of sustained syllables and filled pauses of spontaneous speech were extracted from Malaysian Parliamentary Debate Database of the year 2008. A naïve Bayes was used as a classifier.  ...  Filled pause and Elongation are the two types of speech disfluencies that need more suitable acoustical features to be classified correctly since they are always being misclassified.  ...  The authors fully acknowledged Ministry of Higher Education (MOHE) and Universiti Teknologi MARA Malaysia for the approved fund which makes this important research viable and effective.  ... 
doi:10.24191/mjoc.v4i1.4979 fatcat:x4mkz6645rcsvc2yst2u6l6ttu

Formant characteristics of Malay vowels

Izzad Ramli, Nursuriati Jamil, Norizah Ardi
2020 International Journal of Evaluation and Research in Education (IJERE)  
The findings form the fundamental basis for further research of speech synthesis, speech rehabilitation and speech reproduction of the Malay language.  ...  Analysis of the formant data showed numerous differences between vowels in terms of average frequencies of F1 and F2, and the degree of overlap among adjacent vowels.  ...  The spontaneous speech also suffered with filled pause and elongation that need to be determined and removed to preserve the quality of the spoken words [23 -25] .  ... 
doi:10.11591/ijere.v9i1.20421 fatcat:e4hsdissc5hazdakm35ns2qhe4

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Nik Nur Wahidah Nik Hashim, Nadzirah Ahmad Basri, Mugahed Al-Ezzi Ahmad Ezzi, Nik Mohd Hazrul Nik Hashim
2022 IAES International Journal of Artificial Intelligence (IJ-AI)  
Speech recordings from a total of 43 depressed subjects and 47 healthy subjects were gathered via online platform with diagnosis validation according to the Malay beck depression inventory II (Malay BDI-II  ...  Random forest performed best for male reading speech with 73% accuracy while support vector machine performed best on both male spontaneous speech and female reading speech with 74% and 73% accuracy, respectively  ...  ACKNOWLEDGEMENT This work was supported by funding from the Ministry of Higher Education Malaysia under the Fundamental Research Grant Scheme (FRGS/1/2018/TK04/UIAM/02/7).  ... 
doi:10.11591/ijai.v11.i1.pp238-253 fatcat:uy47uej5gbgmtl32dr7fumgw4u

A Systematic Approach for Malay Language Dialect Identification by Using CNN

Mohd Azman Hanif Sulaiman, Nurhakimah Abd Aziz, Azlee Zabidi, Zuraidah Jantan, Ihsan Mohd Yassin, Megat Syahirul Amin Megat Ali
2021 International Journal of Electrical & Electronic Systems Research (IEESR)  
Speech recognition systems need to be robust to cater for various languages and dialects in order to interact better with humans.  ...  In this paper, works on Malay language dialect identification are presented using Convolution Neural Network (CNN) trained on Mel Frequency Cepstral Coefficient (MFCC) features.  ...  Due to the spontaneous nature of the speech, the recordings suffered from filled pauses and elongation that need to be determined and removed to preserve the dataset quality.  ... 
doi:10.24191/jeesr.v19i1.004 fatcat:6xjqdfb4ajbahlzxuexfh46bxu

Development of Second Language French Oral Skills in an Instructed Setting: A Focus on Speech Ratings

Pavel Trofimovich, Sara Kennedy, Josée Blanchet
2017 Canadian Journal of Applied Linguistics  
These findings are discussed in terms of their implications for L2 pronunciation learning and links between instruction, listener-rated dimensions of speech, and performance in different tasks.  ...  The ratings by 20 French listeners evaluating the speech of 30 adult L2 French learners enrolled in a 15-week listening and speaking course targeting segments, prosody, fluency, and connected speech processes  ...  In L2 French, Prefontaine (2013) showed that acoustic measures of fluency, such as speech and articulation rate, mean length of runs, and pause frequency, were often significantly related to L2 French  ... 
doi:10.7202/1042675ar fatcat:rohj77r2p5bebanfytjrcucwhi

Using automatic alignment to analyze endangered language data: Testing the viability of untrained alignment

Christian DiCanio, Hosung Nam, Douglas H. Whalen, H. Timothy Bunnell, Jonathan D. Amith, Rey Castillo García
2013 Journal of the Acoustical Society of America  
While efforts to document endangered languages have steadily increased, the phonetic analysis of endangered language data remains a challenge.  ...  For instance, additional stop allophones in HMALIGN's phone set aided alignment accuracy.  ...  The current study seeks to fill this gap. A. Forced alignment Progress in speech processing has made it possible to automatically segment transcribed speech.  ... 
doi:10.1121/1.4816491 pmid:23967953 pmcid:PMC5392066 fatcat:lg2o5373vbhkzc67hvw4vhcwtu

Shared-hidden-layer Deep Neural Network for Under-resourced Language the Content

Devin Hoesen, Dessi Puji Lestari, Dwi Hendratmo Widyantoro
2018 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
In this research, the efficacy of augmenting limited Indonesian speech training data with highlyresourced-language training data, such as English, to train Indonesian speech recogniz er was analyzed.  ...  The training was performed in form of shared-hidden-layer deep-neural-network (SHL-DNN) training.  ...  We also would like to thank PT INTI, Bandung, Indonesia for the utilization of the spontaneous speech corpus presented in this research.  ... 
doi:10.12928/telkomnika.v16i0.7984 fatcat:pfn2mjjhi5c6zp325yf4wiy4ue

Evaluating Korean learners' English rhythm proficiency with measures of sentence stress

Ho-Young Lee, Jieun Song
2019 Applied Psycholinguistics  
AbstractPrevious research has suggested that the production of speech rhythm in a second language (L2) or foreign language is influenced by the speaker's first language rhythm.  ...  We examined the production of English rhythm by 75 Korean learners with the rhythm metrics proposed in previous studies (pairwise variability indices and interval measures).  ...  This work was supported by the Seoul National University Research Grant in 2017. The KLEAC database we used for this study was developed in a research project funded by SK Telecom of South Korea.  ... 
doi:10.1017/s0142716419000298 fatcat:ardirh67nzh3poq4qec56egrle

Why final obstruent devoicing is weakening [chapter]

John Harris
2009 Studies in Generative Grammar  
Does the articulatory and aerodynamic distinction between spontaneous and non-spontaneous voicing correlate with some verifiable acoustic distinction that listeners can directly rely on in speech recognition  ...  A modulated-carrier model of strength Speech as a modulated carrier signal Speech can be thought of as a carrier signal modulated by acoustic events.  ... 
doi:10.1515/9783110218596.1.9 fatcat:oqsuomp4gnfslcsvirakumj56e

Prosodic rhythm and African American English

Erik R. Thomas, Phillip M. Carter
2006 English World-Wide  
of the durations of vowels in adjacent syllables.  ...  In order to gain historical perspective, the same technique was applied to the ex-slave recordings described in Bailey, Maynor and Cukor-Avila (1991) and to recordings of five Southern European Americans  ...  In addition to analyzing spontaneous, conversational speech instead of read speech, we deviated in three other ways. First, we dispensed with multiplying the mean of the quotients by 100.  ... 
doi:10.1075/eww.27.3.06tho fatcat:6nhh5gzee5asxbxfjprmtxffce

Acoustic GIS‐based monitoring of Atlantic cod ecosystems in coastal Newfoundland

George A. Rose
2008 Journal of the Acoustical Society of America  
Beyond, this contradiction, specific space analysis models and tools can help to visualize the acoustic interactions between workstations, teams and departments accommodated in the same room.  ...  In this talk we will first give an overview of this evolution from acoustic analogies to computational aeroacoustics ͑CAA͒.  ...  Acoustic validation of the analysis of diadochokinesis in normal speech using the motor speech profile program.  ... 
doi:10.1121/1.2932540 fatcat:v6w3j7upx5duhkunch6oai5jve

The structural acoustic properties of stiffened shells

Yu Luan
2008 Journal of the Acoustical Society of America  
Beyond, this contradiction, specific space analysis models and tools can help to visualize the acoustic interactions between workstations, teams and departments accommodated in the same room.  ...  In this talk we will first give an overview of this evolution from acoustic analogies to computational aeroacoustics ͑CAA͒.  ...  Acoustic validation of the analysis of diadochokinesis in normal speech using the motor speech profile program.  ... 
doi:10.1121/1.2932806 fatcat:zohbewf2k5h7fly2hoqzfdk42e

Trends in preference, programming and design of concert halls for symphonic music

Anders C. Gade
2008 Journal of the Acoustical Society of America  
Rate Analysis ͑DRA͒ in the KayPENTAX Motor Speech Profile.  ...  In view of filling the gap between the low-and the highfrequency domains where modal analysis and statistical methods respectively apply, a technique based on the high resolution analysis algorithm ES-PRIT  ...  in nonnative speech depends on the specific acoustic realization of vowels produced by nonnative speakers.  ... 
doi:10.1121/1.2932471 fatcat:hhka5ml2fvcszklkzau2lw3gka

The Calculation of Dialectoletri over Isolect ofMinangkabau Language in the Origin of Region and Rantau Region [chapter]

Reniwati, Noviatri, Gusti Asnan, Gusdi Sastra
2019 Proceeding of The 4th International Seminar on Linguistics (ISOL-4)  
The number of samples that were used in this study is 210 respondents.  ...  The chosen sample is people who know about the store environment of 212-mart in Padang city, West Sumatra, Indonesia, whose ages started from 16 years old. Acknowledgment  ...  It usually appears during the acoustic process, one of the phenomena that relate to this occurrence was previously explained that when a sound acoustically in between two phonemes is presented in a phonetic  ... 
doi:10.2478/9783110680027-032 fatcat:3mnim7gyvfg67nvcur7eyad7ey
« Previous Showing results 1 — 15 out of 115 results