isolated word speech recognition system

• Technical Articles

Developing an Isolated Word Recognition System in MATLAB

By Daryl Ning, MathWorks

Speech-recognition technology is embedded in voice-activated routing systems at customer call centres, voice dialling on mobile phones, and many other everyday applications. A robust speech-recognition system combines accuracy of identification with the ability to filter out noise and adapt to other acoustic conditions, such as the speaker’s speech rate and accent. Designing a robust speech-recognition algorithm is a complex task requiring detailed knowledge of signal processing and statistical modeling.

This article demonstrates a workflow that uses built-in functionality in MATLAB ® and related products to develop the algorithm for an isolated digit recognition system. The system is speaker-dependent—that is, it recognizes speech only from one particular speaker’s voice.

Classifying Speech-Recognition Systems

Most speech-recognition systems are classified as isolated or continuous. Isolated word recognition requires a brief pause between each spoken word, whereas continuous speech recognition does not. Speech-recognition systems can be further classified as speaker-dependent or speaker-independent. A speaker-dependent system only recognizes speech from one particular speaker's voice, whereas a speaker-independent system can recognize speech from anybody.

The Development Workflow

There are two major stages within isolated word recognition: a training stage and a testing stage. Training involves “teaching” the system by building its dictionary, an acoustic model for each word that the system needs to recognize. In our example, the dictionary comprises the digits ‘zero’ to ‘nine’. In the testing stage we use acoustic models of these digits to recognize isolated words using a classification algorithm.

The development workflow consists of three steps:

• Speech acquisition
• Speech analysis
• User interface development

Acquiring Speech

For training, speech is acquired from a microphone and brought into the development environment for offline analysis. For testing, speech is continuously streamed into the environment for online processing.

During the training stage, it is necessary to record repeated utterances of each digit in the dictionary. For example, we repeat the word ‘one’ many times with a pause between each utterance.

Using the following MATLAB code with a standard PC sound card, we capture ten seconds of speech from a microphone input at 8000 samples per second:

We save the data to disk as ‘ mywavefile.wav ’:

This approach works well for training data. In the testing stage, however, we need to continuously acquire and buffer speech samples, and at the same time, process the incoming speech frame by frame, or in continuous groups of samples.

We use Data Acquisition Toolbox™ to set up continuous acquisition of the speech signal and simultaneously extract frames of data for processing.

The following MATLAB code uses a Windows sound card to capture data at a sampling rate of 8000 Hz. Data is acquired and processed in frames of 80 samples. The process continues until the “RUNNING” flag is set to zero.

Analyzing the Acquired Speech

We begin by developing a word-detection algorithm that separates each word from ambient noise. We then derive an acoustic model that gives a robust representation of each word at the training stage. Finally, we select an appropriate classification algorithm for the testing stage.

Developing a Speech-Detection Algorithm

The speech-detection algorithm is developed by processing the prerecorded speech frame by frame within a simple loop. For example, this MATLAB code continuously reads 160 sample frames from the data in ‘speech’.

To detect isolated digits, we use a combination of signal energy and zero-crossing counts for each speech frame. Signal energy works well for detecting voiced signals, while zero-crossing counts work well for detecting unvoiced signals. Calculating these metrics is simple using core MATLAB mathematical and logical operators. To avoid identifying ambient noise as speech, we assume that each isolated word will last at least 25 milliseconds.

Developing the Acoustic Model

A good acoustic model should be derived from speech characteristics that will enable the system to distinguish between the different words in the dictionary.

We know that different sounds are produced by varying the shape of the human vocal tract and that these different sounds can have different frequencies. To investigate these frequency characteristics we examine the power spectral density (PSD) estimates of various spoken digits. Since the human vocal tract can be modeled as an all-pole filter, we use the Yule-Walker parametric spectral estimation technique from Signal Processing Toolbox™ to calculate these PSDs.

After importing an utterance of a single digit into the variable ‘speech’, we use the following MATLAB code to visualize the PSD estimate:

Since the Yule-Walker algorithm fits an autoregressive linear prediction filter model to the signal, we must specify an order of this filter. We select an arbitrary value of 12, which is typical in speech applications.

Figures 1a and 1b plot the PSD estimate of three different utterances of the words ‘one’ and ‘two’. We can see that the peaks in the PSD remain consistent for a particular digit but differ between digits. This means that we can derive the acoustic models in our system from spectral features.

From the linear predictive filter coefficients, we can obtain several feature vectors using Signal Processing Toolbox functions, including reflection coefficients, log area ratio parameters, and line spectral frequencies.

One set of spectral features commonly used in speech applications because of its robustness is Mel Frequency Cepstral Coefficients (MFCCs). MFCCs give a measure of the energy within overlapping frequency bins of a spectrum with a warped (Mel) frequency scale 1 .

Since speech can be considered to be short-term stationary, MFCC feature vectors are calculated for each frame of detected speech. Using many utterances of a digit and combining all the feature vectors, we can estimate a multidimensional probability density function (PDF) of the vectors for a specific digit. Repeating this process for each digit, we obtain the acoustic model for each digit.

During the testing stage, we extract the MFCC vectors from the test speech and use a probabilistic measure to determine the source digit with maximum likelihood. The challenge then becomes to select an appropriate PDF to represent the MFCC feature vector distributions.

Figure 2a shows the distribution of the first dimension of MFCC feature vectors extracted from the training data for the digit ‘one’.

We could use dfittool in company/newsletters/articles/developing-an-isolated-word-recognition-system-in-matlab.html™ to fit a PDF, but the distribution looks quite arbitrary, and standard distributions do not provide a good fit. One solution is to fit a Gaussian mixture model (GMM), a sum of weighted Gaussians (Figure 2b).

The complete Gaussian mixture density is parameterized by the mixture weights, mean vectors, and covariance matrices from all component densities. For isolated digit recognition, each digit is represented by the parameters of its GMM.

To estimate the parameters of a GMM for a set of MFCC feature vectors extracted from training speech, we use an iterative expectation-maximization (EM) algorithm to obtain a maximum likelihood (ML) estimate. Given some MFCC training data in the variable MFCCtraindata , we use the Statistics and Machine Learning Toolbox gmdistribution function to estimate the GMM parameters. This function is all that is required to perform the iterative EM calculations.

Selecting a Classification Algorithm

After estimating a GMM for each digit, we have a dictionary for use at the testing stage. Given some test speech, we again extract the MFCC feature vectors from each frame of the detected word. The objective is to find the digit model with the maximum a posteriori probability for the set of test feature vectors, which reduces to maximizing a log-likelihood value. Given a digit model gmmmodel and some test feature vectors testdata , the log-likelihood value is easily computed using the posterior function in Statistics and Machine Learning Toolbox:

We repeat this calculation using each digit’s model. The test speech is classified as the digit with the GMM that produces the maximum log-likelihood value.

Building the User Interface

After developing the isolated digit recognition system in an offline environment with prerecorded speech, we migrate the system to operate on streaming speech from a microphone input.We use MATLAB GUIDE tools to create an interface that displays the time domain plot of each detected word as well as the classified digit (Figure 3).

Extending the Application

The algorithm described in this article can be extended to recognize isolated words instead of digits, or to recognize words from several speakers by developing a speaker-independent system.

If the goal is to implement the speech recognition algorithm in hardware, we could use MATLAB and related products to simulate fixed-point effects, automatically generate embedded C code, and verify the generated code.

Published 2010 - 91805v00

Products Used

• Data Acquisition Toolbox
• Signal Processing Toolbox
• Statistics and Machine Learning Toolbox
• Article: Developing Speech-Processing Algorithms for a Cochlear Implant

View Articles for Related Industries

• Communication Devices

Select a Web Site

Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .

You can also select a web site from the following list

How to Get Best Site Performance

Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.

• América Latina (Español)
• Canada (English)
• United States (English)
• Belgium (English)
• Denmark (English)
• Deutschland (Deutsch)
• España (Español)
• Finland (English)
• France (Français)
• Ireland (English)
• Italia (Italiano)
• Luxembourg (English)
• Netherlands (English)
• Norway (English)
• Österreich (Deutsch)
• Portugal (English)
• Sweden (English)
• United Kingdom (English)

Asia Pacific

• Australia (English)
• India (English)
• New Zealand (English)

Contact your local office

• Contact sales

• Corpus ID: 18333316

ISOLATED WORD SPEECH RECOGNITION SYSTEM USING DYNAMIC TIME WARPING

• R. Makhijani , R. Gupta , M. Scholar
• Published 2013
• Computer Science

Figures from this paper

7 Citations

Speaker independent speech recognition using maximum likelihood approach for isolated words, analysis of feature extraction methods for speaker dependent speech recognition, analysis of voice recognition algorithms using matlab, single voice command recognition by finite element analysis, hardware design of dynamic time warping algorithm based on fpga in verilog, automatic home appliance switching using speech recognition software and embedded system, speech-based vehicle movement control solution, 14 references, real time isolated word speech recognition system for human computer interaction, speech recognition with dynamic time warping using matlab, dynamic time warping.

• Highly Influential

Isolated malay speech recognition using Hidden Markov Models

Robust speech recognition using fusion techniques and adaptive filtering, speech recognition using dynamic time warping, speech recognition by machine: a review, statistical modeling in continuous speech recognition (csr), the use of a one-stage dynamic programming algorithm for connected word recognition, related papers.

Showing 1 through 3 of 0 Related Papers

An automatic speech recognition system for isolated Amazigh word using 1D & 2D CNN-LSTM architecture

• Published: 11 October 2023
• Volume 26 , pages 775–787, ( 2023 )

Cite this article

• Mohamed Daouad   ORCID: orcid.org/0009-0007-6492-2513 1 ,
• Fadoua Ataa Allah   ORCID: orcid.org/0000-0001-7091-4412 2 &
• El Wardani Dadi   ORCID: orcid.org/0000-0003-2946-854X 1  

190 Accesses

3 Citations

Explore all metrics

The availability of automatic speech recognition systems is crucial in various domains such as communication, healthcare, security, education, etc. However, currently, the existing systems often favor dominant languages such as English, French, Arabic, or Asian languages, leaving under-resourced languages without the consideration they deserve. In this specific context, our work is focused on the Amazigh language, which is widely spoken in North Africa. Our primary objective is to develop an automatic speech recognition system specifically for isolated words, with a particular focus on the Tarifit dialect spoken in the Rif region of Northern Morocco. For the dataset construction, we considered 30 isolated words recorded from 80 diverse speakers, resulting in 2400 audio files. The collected corpus is characterized by its quantity, quality, and variety. Moreover, the dataset serves as a valuable resource for further research and development in the field, supporting the advancement of speech recognition technology for underrepresented languages. For the recognition system, we have chosen the most recent approach in the field of speech recognition, which is a combination of convolutional neural networks and LSTM (CNN-LSTM). For the test, we have evaluated two different architectural models: the 1D CNN LSTM and the 2D CNN LSTM. The experimental results demonstrate a remarkable accuracy rate of over 96% in recognizing spoken words utilizing the 2D CNN LSTM architecture.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Recognition Method of Wa Language Isolated Words Based on Convolutional Neural Network

Isolated Word Automatic Speech Recognition System

An acoustic model and linguistic analysis for Malayalam disyllabic words: a low resource language

Data availability.

The data used in this study are not publicly available due to restrictions imposed by the LSA Laboratory. However, the data can be made available by the corresponding author upon reasonable request.

Abakarim, F., & Abenaou, A. (2020). Amazigh isolated word speech recognition system using the adaptive orthogonal transform method. 2020 International conference on intelligent systems and computer vision . https://doi.org/10.1109/ISCV49265.2020.9204291

Article   Google Scholar  

Abdullah, M., Ahmad, M., & Han, D. (2020). Facial expression recognition in videos: An CNN-LSTM based model for video classification. In 2020 International conference on electronics, information, and communication (ICEIC) (pp. 16–18). IEEE. https://doi.org/10.1109/ICEIC49074.2020.9051332

Ameur, M., Bouhjar, A., Boukhris, F., Boukouss, A., Boumalk, A., Elmedlaoui, M., El Mehdi, I., & Souifi, H. (2004). Initiation à la langue amazighe . El Maârif al Jadida.

Badshah, A. M., Rahim, N., Ullah, N., Ahmad, J., Muhammad, K., Lee, M. Y., Kwon, S., & Baik, S. W. (2019). Deep features-based speech emotion recognition for smart affective services. Multimedia Tools and Applications, 78 (5), 5571–5589. https://doi.org/10.1007/s11042-017-5292-7

Barkani, F., Hamidi, M., Laaidi, N., Zealouk, O., Satori, H., & Satori, K. (2023). Amazigh speech recognition based on the Kaldi ASR toolkit. International Journal of Information Technology . https://doi.org/10.1007/s41870-023-01354-z

Boukous, A. (1995). Société, langues et cultures au maroc : Enjeux symboliques (8th ed., p. 239). Faculté des Lettres et des Sciences Humaines, Université Mohamed V.

Google Scholar  

Choi, K., Fazekas, G., Sandler, M., & Cho, K. (2018). A comparison of audio signal preprocessing methods for deep neural networks on music tagging. European Signal Processing Conference, 2018 , 1870–1874. https://doi.org/10.23919/EUSIPCO.2018.8553106

El Ouahabi, S., Atounti, M., & Bellouki, M. (2017). A database for Amazigh speech recognition research: AMZSRD. In Proceedings of 2017 International conference of cloud computing technologies and applications, CloudTech 2017, 2018-Janua (pp. 1–5). IEEE. https://doi.org/10.1109/CloudTech.2017.8284715

El Ouahabi, S., Atounti, M., & Bellouki, M. (2019a). Amazigh speech recognition using triphone modeling and clustering tree decision. Annals of the University of Craiova Mathematics and Computer Science Series, 46 (1), 55–65.

El Ouahabi, S., Atounti, M., & Bellouki, M. (2019b). Toward an automatic speech recognition system for Amazigh-tarifit language. International Journal of Speech Technology, 22 (2), 421–432. https://doi.org/10.1007/s10772-019-09617-6

El Ouahabi, S., Atounti, M., & Bellouki, M. (2020). Optimal parameters selected for automatic recognition of spoken Amazigh digits and letters using hidden Markov model toolkit. International Journal of Speech Technology, 23 (4), 861–871. https://doi.org/10.1007/s10772-020-09762-3

Essa, Y., Hunt, H. G. P., Gijben, M., & Ajoodha, R. (2022). Deep learning prediction of thunderstorm severity using remote sensing weather data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15 , 4004–4013. https://doi.org/10.1109/JSTARS.2022.3172785

Fadoua, A. A., & Siham, B. (2012). Natural language processing for Amazigh language: Challenges and future directions. Language Technology for Normalisation of Less-Resourced Languages, 19 , 23.

Hajarolasvadi, N., & Demirel, H. (2019). 3D CNN-based speech emotion recognition using k-means clustering and spectrograms. Entropy, 21 (5), 479. https://doi.org/10.3390/e21050479

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9 (8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Idhssaine, A., & El Kirat, Y. (2021). Amazigh language use, perceptions and revitalisation in morocco: The case of rabat-sale region. Journal of North African Studies, 26 (3), 465–479. https://doi.org/10.1080/13629387.2019.1690996

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60 (6), 84–90. https://doi.org/10.1145/3065386

Lee, J., & Tashev, I. (2015). High-level feature representation using recurrent neural network for speech emotion recognition. In Proceedings of the annual conference of the international speech communication association, INTERSPEECH , 2015 - Janua (pp. 1537–1540). https://doi.org/10.21437/interspeech.2015-336

Oruh, J., Viriri, S., & Adegun, A. (2022). Long short-term memory recurrent neural network for automatic speech recognition. IEEE Access, 10 , 30069–30079. https://doi.org/10.1109/ACCESS.2022.3159339

Ouhnini, A., Aksasse, B., & Ouanan, M. (2023). Towards an automatic speech-to-text transcription system: Amazigh language. International Journal of Advanced Computer Science and Applications, 14 (2), 413–418. https://doi.org/10.14569/IJACSA.2023.0140250

Satori, H., & Elhaoussi, F. (2014). Investigation amazigh speech recognition using CMU tools. International Journal of Speech Technology, 17 (3), 235–243. https://doi.org/10.1007/s10772-014-9223-y

Telmem, M., & Ghanou, Y. (2020). A comparative study of HMMs and CNN acoustic model in amazigh recognition system. Advances in Intelligent Systems and Computing, 1076 , 533–540. https://doi.org/10.1007/978-981-15-0947-6_50

Telmem, M., & Ghanou, Y. (2021). The convolutional neural networks for Amazigh speech recognition system. Telkomnika (Telecommunication Computing Electronics and Control), 19 (2), 515–522. https://doi.org/10.12928/TELKOMNIKA.v19i2.16793

Vankdothu, R., Hameed, M. A., & Fatima, H. (2022). A brain tumor identification and classification using deep learning based on CNN-LSTM method. Computers and Electrical Engineering, 101 (November 2021), 107960. https://doi.org/10.1016/j.compeleceng.2022.107960

Zealouk, O., Satori, H., Laaidi, N., Hamidi, M., & Satori, K. (2020). Noise effect on Amazigh digits in speech recognition system. International Journal of Speech Technology, 23 (4), 885–892. https://doi.org/10.1007/s10772-020-09764-1

Download references

No funding was received for conducting this study. The authors declare they have no financial interests.

Author information

Authors and affiliations.

LSA laboratory, ENSAH, SOVIA Team, University of Abdelmalek Essaadi, Tetouan, Morocco

Mohamed Daouad & El Wardani Dadi

CEISIC, The Royal Institute of the Amazigh Culture, Rabat, Morocco

Fadoua Ataa Allah

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Mohamed Daouad .

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Daouad, M., Allah, F.A. & Dadi, E.W. An automatic speech recognition system for isolated Amazigh word using 1D & 2D CNN-LSTM architecture. Int J Speech Technol 26 , 775–787 (2023). https://doi.org/10.1007/s10772-023-10054-9

Download citation

Received : 22 June 2023

Accepted : 29 September 2023

Published : 11 October 2023

Issue Date : September 2023

DOI : https://doi.org/10.1007/s10772-023-10054-9

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Amazigh language
• Convolutional neural network
• Deep learning
• Spectrogram
• Speech recognition
• Find a journal
• Publish with us
• Track your research

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings
• My Bibliography
• Collections
• Citation manager

Save citation to file

Email citation, add to collections.

• Create a new collection
• Add to an existing collection

Add to My Bibliography

Your saved search, create a file for external citation management software, your rss feed.

• Search in PubMed
• Search in NLM Catalog
• Add to Search

Application of an Isolated Word Speech Recognition System in the Field of Mental Health Consultation: Development and Usability Study

Affiliation.

• 1 Liberal Arts College, Hunan Normal University, Changsha, China.
• PMID: 32384054
• PMCID: PMC7301261
• DOI: 10.2196/18677

Background: Speech recognition is a technology that enables machines to understand human language.

Objective: In this study, speech recognition of isolated words from a small vocabulary was applied to the field of mental health counseling.

Methods: A software platform was used to establish a human-machine chat for psychological counselling. The software uses voice recognition technology to decode the user's voice information. The software system analyzes and processes the user's voice information according to many internal related databases, and then gives the user accurate feedback. For users who need psychological treatment, the system provides them with psychological education.

Results: The speech recognition system included features such as speech extraction, endpoint detection, feature value extraction, training data, and speech recognition.

Conclusions: The Hidden Markov Model was adopted, based on multithread programming under a VC2005 compilation environment, to realize the parallel operation of the algorithm and improve the efficiency of speech recognition. After the design was completed, simulation debugging was performed in the laboratory. The experimental results showed that the designed program met the basic requirements of a speech recognition system.

Keywords: HMM; hidden Markov model; isolated words; mental health; programming; small vocabulary; speech recognition.

©Weifeng Fu. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 03.06.2020.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Block diagram of speech recognition…

Block diagram of speech recognition system.

References use templates as word…

References use templates as word units. HMM: Hidden Markov Model.

Mel Frequency Cepstral Coefficient (MFCC)…

Mel Frequency Cepstral Coefficient (MFCC) calculation flow diagram. FFT: fast Fourier transform.

Mel Frequency Cepstral Coefficient (MFCC) scale corresponding curve.

Similar articles

• Frontier Research on Low-Resource Speech Recognition Technology. Slam W, Li Y, Urouvas N. Slam W, et al. Sensors (Basel). 2023 Nov 10;23(22):9096. doi: 10.3390/s23229096. Sensors (Basel). 2023. PMID: 38005483 Free PMC article. Review.
• Geospatial assistive technologies for wheelchair users: a scoping review of usability measures and criteria for mobile user interfaces and their potential applicability. Prémont MÉ, Vincent C, Mostafavi MA, Routhier F. Prémont MÉ, et al. Disabil Rehabil Assist Technol. 2020 Feb;15(2):119-131. doi: 10.1080/17483107.2018.1539876. Epub 2019 Jan 21. Disabil Rehabil Assist Technol. 2020. PMID: 30663444 Review.
• Effect of training on word-recognition performance in noise for young normal-hearing and older hearing-impaired listeners. Burk MH, Humes LE, Amos NE, Strauser LE. Burk MH, et al. Ear Hear. 2006 Jun;27(3):263-78. doi: 10.1097/01.aud.0000215980.21158.a2. Ear Hear. 2006. PMID: 16672795
• Development of a speech-based dialogue system for report dictation and machine control in the endoscopic laboratory. Molnar B, Gergely J, Toth G, Pronai L, Zagoni T, Papik K, Tulassay Z. Molnar B, et al. Endoscopy. 2000 Jan;32(1):58-61. doi: 10.1055/s-2000-136. Endoscopy. 2000. PMID: 10691274
• Adaptive communication systems for patients with mobility disorders. Zimmer CA, Devlin PM, Werner JL, Stamp CV, Bellian KT, Powell DM, Edlich RF. Zimmer CA, et al. J Burn Care Rehabil. 1991 Jul-Aug;12(4):354-60. J Burn Care Rehabil. 1991. PMID: 1834676
• Boussaid L, Hassine M. Arabic isolated word recognition system using hybrid feature extraction techniques and neural network. Int J Speech Technol. 2017 Nov 23;21(1):29–37. doi: 10.1007/s10772-017-9480-7. - DOI
• Bennettlevy J, Martin E, Bridgman H, Carey T.A, Isaacs A. N, Little F. Mental health academics in rural and remote Australia. Rural and remote health. 2016;16(3):3793–3793. - PubMed
• Wu S. A Traffic Motion Object Extraction Algorithm. Int J Bifurcation Chaos. 2016 Jan 14;25(14):1540039. doi: 10.1142/s0218127415400398. - DOI
• Fujii Y, Fujii K, Yoon J, Sugahara H, Kitano N, Okura T. The Effects Of Low-intensity Exercise On Depressive Symptoms In Socially-isolated Older Adults. Medicine & Science in Sports & Exercise. 2016;48:1052. doi: 10.1249/01.mss.0000488166.06405.c1. - DOI
• Elovainio M, Hakulinen C, Pulkki-Råback L, Virtanen M, Josefsson K, Jokela M, Vahtera J, Kivimäki M. Contribution of risk factors to excess mortality in isolated and lonely individuals: an analysis of data from the UK Biobank cohort study. The Lancet Public Health. 2017 Jun;2(6):e260–e266. doi: 10.1016/s2468-2667(17)30075-0. - DOI - PMC - PubMed

Related information

Linkout - more resources, full text sources.

• Europe PubMed Central
• JMIR Publications
• PubMed Central

Miscellaneous

• NCI CPTAC Assay Portal
• Citation Manager

NCBI Literature Resources

MeSH PMC Bookshelf Disclaimer

The PubMed wordmark and PubMed logo are registered trademarks of the U.S. Department of Health and Human Services (HHS). Unauthorized use of these marks is strictly prohibited.

IEEE Account

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

ISOLATED WORD SPEECH RECOGNITION SYSTEM USING HTK

2014, TJPRC

This paper proposes a system of Isolated Word Speech Recognition for Tamil language using Hidden Markov Model (HMM) approach. The most powerful Mel Frequency Cepstral Coefficients (MFCC) feature extraction technique is used to train the acoustic features of the speech database. The triphone based acoustic model is chosen to recognize the given Tamil digits. This system is a small vocabulary system where it is trained to identify the Tamil digits from one to ten. The result analysis of HTK (HMM Tool Kit) shows 90% of recognition accuracy at the word level.

Related Papers

— Speech recognition is the process of converting an acoustic waveform into the text similar to the information being conveyed by the speaker. In this paper implementation of isolated words and connected words Automatic Speech Recognition system (ASR) for the words of Hindi language will be discussed. The HTK (hidden markov model toolkit) based on Hidden Markov Model (HMM), a statistical approach, is used to develop the system. Initially the system is trained for 100 distinct Hindi words .This paper also describes the working of HTK tool, which is used in various phases of ASR system, by presenting a detailed architecture of an ASR system developed using various HTK library modules and tools. The recognition results will show that the overall system accuracy for isolated words is 95% and for connected words is 90%. Index Terms— HMM, HTK, Mel Frequency Cepstral Coefficient (MFCC), Automatic Speech Recognition (ASR), Hindi, Isolated word ASR, connected word ASR.

Mohamed Kalith Ibralebbe

Speech recognition technology has improved with time to enhanced Human Computer Interaction (HCI).This paper proposed a system for isolated to connected Tamil digit speech recognition system using CMU Sphinx tools. The connected speech recognition important in many application such as voice-dialling telephone, automated banking system automated data entry, pin entry etc. the proposed system is tri phone based, small vocabularies, speaker specific and speaker-independent. The most powerful Mel Frequency Cepstral Coefficient (MFCC) feature extraction techniques are used to train the acoustic feature of speech database. The probabilistic Hidden Markov Model (HMM) is used to model the speech utterance. And the Viterbi beam search algorithm is used in decoding process. The system tested with random digit (0 to 100) in a various condition shows optimum result 96.7% recognition rates for speaker specific and 54.5% recognition rate for speaker independent in connected word recognition. We use CMU sphinx speech recognition tools to construction of speech recognizer.

amritesh raj

nikita dhanvijay

This paper is based on SR system. In the speech recognition process computer takes a voice signal which is recorded using a microphone and converted into words in real-time. This SR system has been developed using different feature extraction techniques which include MFCC, HMM. All are used as the classifier. ASR i.e. automated speech recognition is program or we can called it as a machine, and it has ability to recognize the voice signal (speech signal or voice commands) or take dictation which involves the ability to match a voice pattern opposite to a given vocabulary. HTK i.e. The Hidden Markov model Toolkit is used to develop the SR System. HMM consist of the Acoustic word model which is used to recognize the isolated word. In this paper, we collect Hindi database, with a vocabulary size a bit extended. HMM has been implemented using the HTK Toolkit.

IJESRT Journal

This paper is based on SR system. In the speech recognition process computer takes a voice signal which is recorded using a microphone and converted into words in real-time. This SR system has been developed using different feature extraction techniques which include MFCC, HMM. All are used as the classifier. ASR i.e. automated speech recognition is program or we can called it as a machine, and it has ability to recognize the voice signal (speech signal or voice commands) or take dictation which involves the ability to match a voice pattern opposite to a given vocabulary. HTK i.e. The Hidden Markov model Toolkit is used to develop the SR System. HMM consist of the Acoustic word model which is used to recognize the isolated word. In this paper, we collect Hindi database, with a vocabulary size a bit extended. HMM has been implemented using the HTK Toolkit. KEYWORDS: HMM (hidden markov model), ASR (Automatic Speech Recognition), Speech recognition (SR). MFCC (mel frequency cepestral coefficient)

Ishan Bhardwaj

International Journal of Engineering Research and Technology (IJERT)

IJERT Journal

https://www.ijert.org/sanskrit-speech-recognition-using-hidden-markov-model-toolkit https://www.ijert.org/research/sanskrit-speech-recognition-using-hidden-markov-model-toolkit-IJERTV3IS100141.pdf Automated Speech Recognition (ASR) is the ability of a machine or program to recognize the voice commands or take dictation which involves the ability to match a voice pattern against a provided or acquired vocabulary. At present, mainly Hidden Markov Model (HMMs) based speech recognizers are used. This research work aims to build a speech recognition system for Sanskrit language. Hidden Markov Model Toolkit (HTK) is used to develop the system. The system is trained to recognize 50 Sanskrit utterances. Training data has been collected from ten speakers. The experimental results show that the overall accuracy of the presented system with 5 state and 10 states in HMM topology is 95.2% to 97.2% respectively.

International Journal of Physical Sciences

Mondher Frikha

iswarya ganesh

In recent years, Human-Computer Interaction is one of the upcoming technologies which allows human to communicate with computer by speech and enables machine to understand human communication. Speech Recognition is the fascinating field in Human-Computer Interaction which has attained certain level of maturity in English language and still startup level in Indian languages. Most widely used feature extraction technique in digital signal processing is Linear Predictive Cepstral Coefficient and Mel Frequency Cepstral Coefficient. This paper presents comparative analysis of Linear Predictive Cepstral Coefficient and Mel Frequency Cepstral Coefficient feature extraction methods for isolated speech database in Tamil language. Probabilistic neural network is widely used in research to find more efficient classification solutions. From each speech sample frame 8, 12 and 24 feature vectors of Linear Predictive cepstral coefficient and Mel frequency cepstral coefficient are extracted and classified using probabilistic neural network. The experimental results shows that 24 feature vectors extracted using Mel frequency cepstral coefficient provides better recognition accuracy of 97% for isolated Tamil words, when compared with 8,12- Mel frequency cepstral coefficient and 8,12,24- Linear Predictive cepstral coefficient feature vectors respectively.

Abdullah - al - mamun

here we present a model of isolated speech recognition (ISR) system for Bangla character set and analysis the performance of that recognizer model. In this isolated Bangla speech recognition is implemented by the combining MFCC as feature extraction for the input audio file and used Hidden Markov Model (HMM) for training & recognition due to HMMs uncomplicated and effective framework for modeling time-varying sequence of spectral feature vector. A series of experiments have been performed with 10-talkers (5 male and 5 female) by 56 Bangla characters (include, Bangla vowel, Bangla consonant, Bangla

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

RELATED PAPERS

International Journal of Recent Technology and Engineering

anand unnibhavi

Achyuta Nand Mishra

Shweta Sinha

Cini Kurian

International Journal of Engineering Sciences & Research Technology

Ijesrt Journal

Journal of Signal and Information Processing

PROF MAHUA BHATTACHARYA

Computing Research Repository

Hemakumar Gopal

Elizabeth Sherly

International Journal of Computer Applications

Neeta Awasthy

Current Journal of Applied Science and Technology

David Asirvatham

Journal of Physics: Conference Series

Nindian Puspa Dewi

IJSRD Journal

Intl. J. of Multidisciplinary Research and Development

Md. Mijanur Rahman , Ashraful Kadir

Engineering Advancements RSEA

Supun Molligoda

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

neha baranwal

bhargab Medhi

Professor (Dr.) Ratnadeep R . Deshmukh

Dalmiya C P

vikram karimella

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024