2012
DOI: 10.5120/8217-1639
|View full text |Cite
|
Sign up to set email alerts
|

Speaker Dependent and Independent Isolated Hindi Word Recognizer using Hidden Markov Model (HMM)

Abstract: Hindi is very complex language with large number of phonemes and being used with various ascents in different regions in India. In this manuscript, speaker dependent and independent isolated Hindi word recognizers using the Hidden Markov Model (HMM) is implemented, under noisy environment. For this study, a set of 10 Hindi names has been chosen as a test set for which the training and testing is performed. The scheme instigated here implements the Mel Frequency Cepstral Coefficients (MFCC) in order to compute … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
3
0

Year Published

2014
2014
2018
2018

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 51 publications
0
3
0
Order By: Relevance
“…If the phoneme has high or low resolution to the other class (interclass confusion), the visual information is complementary to the audio information due to the different shape of visemes for different classes [8,9]. However if the phoneme has confusion with the same viseme class (intraclass confusion) then visual information is not always useful because it has same viseme shape for same class.…”
Section: Introductionmentioning
confidence: 94%
See 1 more Smart Citation
“…If the phoneme has high or low resolution to the other class (interclass confusion), the visual information is complementary to the audio information due to the different shape of visemes for different classes [8,9]. However if the phoneme has confusion with the same viseme class (intraclass confusion) then visual information is not always useful because it has same viseme shape for same class.…”
Section: Introductionmentioning
confidence: 94%
“…The experiment has shown 79.11% recognition rate for the proposed system. Bhardwaj et al [8] has been prepared a dataset of 10 words which has been spoken by 10 speakers. MFCC and HMM are used for the feature extraction and classification respectively.…”
Section: Introductionmentioning
confidence: 99%
“…These attributes help identify the speaker and speech features [4]. Although speech recognition and speaker recognition are different fields, the feature extraction methods in both fields overlap [5]. These methods include predictive models based on the linear predictive coding coefficient (LPCC), perceptual linear prediction (PLP), mel frequency cepstral coefficient (MFCC) and relative spectra filtering (RASTA).…”
Section: Introductionmentioning
confidence: 99%