scholarly journals A Novel Text to Speech Technique for Tamil Language using Hidden Markov Models (HMM)

2019 ◽  
Vol 8 (10) ◽  
pp. 38-47
Keyword(s):  
Signal Processing ◽  
Markov Model ◽  
Speech Processing ◽  
Major Part ◽  
Markov Models ◽  
Hidden Markov ◽  
Digital Signal ◽  
Text To Speech ◽  
Traditional System ◽  
Local Languages

Application of digital signal processing in speech processing plays a major part in our everyday life. Text to speech system lets people to see and read out loud consecutively. Text-to-speech synthesizers use synthesis techniques that require good quality speech. Text to speech conversion (TTS) can apply to many applications such as automation, audio recording and audio-based assistance system. Text to speech conversion can be applied for various multinational language as well as for a number of local languages. An efficient text to speech conversion for Tamil language with extreme accuracy is proposed in this work. Multi feature, with a Hidden Markov Model (HMM) predictor is used to convert text to speech efficiently. By using the proposed method, the precision of the framework is enhanced by a factor of 6% when contrasted with the traditional system.

scholarly journals Performing Text – To – Speech based Hidden Markov Model on Digital Signal Processing platform

2014 ◽  
Vol 17 (1) ◽  
pp. 32-38
Author(s):  
Nhat Truong Minh Vu ◽  
Binh Hieu Nguyen ◽  
Nhat Minh Pham ◽  
Thuan Huu Huynh ◽  
Tu Trong Bui ◽  
...  
Keyword(s):  
Signal Processing ◽  
Digital Signal Processing ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hardware Implementation ◽  
Hidden Markov ◽  
Digital Signal ◽  
Text To Speech ◽  
Processing Platform

Text To Speech (TTS) using Hidden Markov Model (HMM) has become popular in recent years. However, because most of such systems were implemented on personal computers (PCs), it is difficult to offer these systems to real applications. In this paper, we present a hardware implementation of TTS based on DSP architecture, which is applicable for real applications. By optimizing hardware architecture, the quality of the DSP-based synthesized speech is nearly identical to that synthesized on PCs.

scholarly journals Aplikasi Pengenalan Suara untuk Pengamanan Software Komputer Menggunakan Metode MFCC(Mel Frequency Cepstrum Coefficients) dan HMM (Hidden Markov Model)

2020 ◽  
Vol 11 (1) ◽  
pp. 39
Author(s):  
Ichbal Septian El Bashart ◽  
Triyanto Pangaribowo
Keyword(s):  
Signal Processing ◽  
Digital Signal Processing ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Digital Signal ◽  
Mel Frequency Cepstral Coefficient

Proses pengolahan sinyal suara dapat menggunakan digital signal processing dan algoritma tertentu yang dapat mengolah baik itu dengan fungsi matematis ataupun persamaan sehingga dapat dikenali. Suara sendiri memiliki sinyal informasi yang tidak terbatas dan memiliki banyak kegunaan penerapan sehari – hari termasuk diantaranya adalah untuk proses kontrol dan identifikasi aplikasi komputer misalnya. Perancangan aplikasi pengenalan suara untuk membuka aplikasi komputer berdasar pengguna nya dilakukan dengan 2 proses utama yaitu dengan menggunakan algoritma untuk ekstraksi pencocokan ciri. Ekstraksi ciri merupakan fitur untuk mendapatkan ciri atau elemen suara yang bisa membeda bedakan masing-masing suara manusia. Metode yang digunakan dalam tugas akhir ini untuk ekkstraksi suara adalah MFCC (Mel Frequency Cepstral Coefficient). Proses selanjutnya adalah pencocokan fitur ciri dengan menggunakan HMM (Hidden Markov Model). Hasil pengujian dari penelitian ini dapat diketahui apabila semakin adanya kemiripan suara saat pengujian dengan saat pelatihan maka aplikasi yang terbuka akan sesuai dengan aplikasi yang disuarakan. Hasil pengujian suara untuk mengenali suara yang ada pada database suara yang tertinggi 80% dan untuk suara diluar database hanya 0-40%, dengan kondisi aplikasi yang terbuka masih ada perbedaan antara aplikasi yang diinginkan dengan hasil keputusan sistem

scholarly journals A copula-based multivariate hidden Markov model for modelling momentum in football

2021 ◽  
Author(s):  
Marius Ötting ◽  
Roland Langrock ◽  
Antonello Maruotti
Keyword(s):  
Markov Model ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
State Dependence ◽  
Change Points ◽  
Sports Fans ◽  
Modelling Framework ◽  
State Dependent ◽  
Different Levels

AbstractWe investigate the potential occurrence of change points—commonly referred to as “momentum shifts”—in the dynamics of football matches. For that purpose, we model minute-by-minute in-game statistics of Bundesliga matches using hidden Markov models (HMMs). To allow for within-state dependence of the variables, we formulate multivariate state-dependent distributions using copulas. For the Bundesliga data considered, we find that the fitted HMMs comprise states which can be interpreted as a team showing different levels of control over a match. Our modelling framework enables inference related to causes of momentum shifts and team tactics, which is of much interest to managers, bookmakers, and sports fans.

scholarly journals The Application of Baum-Welch Algorithm in Multistep Attack

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Yanxue Zhang ◽  
Dongmei Zhao ◽  
Jinxing Liu
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov Models ◽  
Viterbi Algorithm ◽  
Markov Models ◽  
Hidden Markov ◽  
Simulation Experiments ◽  
Forward Algorithm ◽  
Better Than

The biggest difficulty of hidden Markov model applied to multistep attack is the determination of observations. Now the research of the determination of observations is still lacking, and it shows a certain degree of subjectivity. In this regard, we integrate the attack intentions and hidden Markov model (HMM) and support a method to forecasting multistep attack based on hidden Markov model. Firstly, we train the existing hidden Markov model(s) by the Baum-Welch algorithm of HMM. Then we recognize the alert belonging to attack scenarios with the Forward algorithm of HMM. Finally, we forecast the next possible attack sequence with the Viterbi algorithm of HMM. The results of simulation experiments show that the hidden Markov models which have been trained are better than the untrained in recognition and prediction.

scholarly journals Utilizing Gaze Behavior for Inferring Task Transitions Using Abstract Hidden Markov Models

2016 ◽  
Vol 19 (58) ◽  
pp. 1
Author(s):  
Daniel Fernando Tello Gamarra
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Hand Movement ◽  
Gaze Behavior ◽  
Improved Method ◽  
The Relationship

We demonstrate an improved method for utilizing observed gaze behavior and show that it is useful in inferring hand movement intent during goal directed tasks. The task dynamics and the relationship between hand and gaze behavior are learned using an Abstract Hidden Markov Model (AHMM). We show that the predicted hand movement transitions occur consistently earlier in AHMM models with gaze than those models that do not include gaze observations.

Speech Disorders Recognition using Speech Analysis

2013 ◽  
pp. 494-507 ◽  
Author(s):  
Khaled Necibi ◽  
Halima Bahi ◽  
Toufik Sari
Keyword(s):  
Signal Processing ◽  
Hidden Markov Models ◽  
Automatic Speech Recognition ◽  
Markov Models ◽  
Hidden Markov ◽  
Speech Disorders ◽  
Speech Analysis ◽  
Physical Problems ◽  
Processing Techniques ◽  
Signal Processing Techniques

Speech disorders are human disabilities widely present in young population but also adults may suffer from such disorders after some physical problems. In this context, the detection and further the correction of such disabilities may be handled by Automatic Speech Recognition (ASR) technology. The first works on the speech disorders detection began early in the 70s and seem to follow the same evolution as those on the ASR. Indeed, these early works were more based on the signal processing techniques. Progressively, systems dealing with speech disorders incorporate more ideas from ASR technology. Particularly, Hidden Markov Models, the state-of-the-art approaches in ASR systems, are used. This chapter reviews systems that use ASR techniques to evaluate pronunciation of people who suffer from speech or voice impairments. The authors investigate the existing systems and present the main innovation and some of the available resources.

scholarly journals A Hidden Markov Model for the Linguistic Analysis of the Voynich Manuscript

2019 ◽  
Vol 24 (1) ◽  
pp. 14 ◽  
Author(s):  
Luis Acedo
Keyword(s):  
Time Series ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Mathematical Linguistics ◽  
Underlying Structure ◽  
Internal States ◽  
Consonant Sounds

Hidden Markov models are a very useful tool in the modeling of time series and any sequence of data. In particular, they have been successfully applied to the field of mathematical linguistics. In this paper, we apply a hidden Markov model to analyze the underlying structure of an ancient and complex manuscript, known as the Voynich manuscript, which remains undeciphered. By assuming a certain number of internal states representations for the symbols of the manuscripts, we train the network by means of the α and β -pass algorithms to optimize the model. By this procedure, we are able to obtain the so-called transition and observation matrices to compare with known languages concerning the frequency of consonant andvowel sounds. From this analysis, we conclude that transitions occur between the two states with similar frequencies to other languages. Moreover, the identification of the vowel and consonant sounds matches some previous tentative bottom-up approaches to decode the manuscript.

Hidden Markov model interpretations of neural networks

2000 ◽  
Vol 23 (4) ◽  
pp. 494-495
Author(s):  
Ingmar Visser
Keyword(s):  
Neural Networks ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Distributed Representations ◽  
Hidden Layer

Page's manifesto makes a case for localist representations in neural networks, one of the advantages being ease of interpretation. However, even localist networks can be hard to interpret, especially when at some hidden layer of the network distributed representations are employed, as is often the case. Hidden Markov models can be used to provide useful interpretable representations.

Sign in / Sign up

Export Citation Format

Share Document