Speaker independent continuous speech and isolated digit recognition using VQ and HMM

Revathi, A.; Venkataramani, Y.

doi:10.1109/iccsp.2011.5739300

Cited by 22 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, for each tone with an actual frequency f, measured in Hz, a subjective pitch is measured on a scale called the "mel scale" [9]. The Mel frequency scale is linear frequency spacing below 1000 Hz and a logarithmic spacing above 1000Hz [5]. To compute the Mel for a given frequency f in Hz, a following formula is used.…”

Section: : Mel Filter Bankmentioning

confidence: 99%

Isolated Words Recognition Using Mfcc, LPC and Neural Network

Gamit¹

2015

IJRET

View full text Add to dashboard Cite

Automatic speech recognition is an important topic of speech processing. This paper presents the use of an Artificial Neural Network (ANN) for isolated word recognition. The Pre-processing is done and voiced speech is detected based on energy and zero crossing rates (ZCR). The proposed approach used in speech recognition is Mel Frequency Cepstral Coefficients (MFCC) and combine features of both MFCC and Linear Predictive Coding (LPC). The back-propagation is used as a classifier. The recognition accuracy is increased when combine features of both LPC and MFCC are used as compared to only MFCC approach using Neural Network as a classifier..

show abstract

Section: : Mel Filter Bankmentioning

confidence: 99%

Isolated Words Recognition Using Mfcc, LPC and Neural Network

Gamit¹

2015

IJRET

View full text Add to dashboard Cite

show abstract

“…With the speech recognition library, we can process the user's query and respond by providing the requested information to the user. Speech recognition is the ability to receive and interpret dictation to understand and carry out given commands [5]. Voice recognition has gained prominence and use with the rise of AI and intelligent assistant.…”

Section: Introductionmentioning

confidence: 99%

Smart Voice Assistant for Library System

S¹,

Prathinan²,

Suresh³

et al. 2020

Int. Res. J. multidiscip. Technovation

View full text Add to dashboard Cite

Library plays an important role in student’s life. It is also helpful for the research scholars. Today libraries are established in all places. Finding a book in the library is a herculean task. Some people even loose interest while searching the required book. Searching for books in computer also takes much time. In our project we use voice recognition to find books which will make the herculean task easier. Even the people without system knowledge can access this and find books in an easier way. It reduces the time in searching books and makes the library user friendly.

show abstract

“…There are a number of situations in which correct recognition of person is required. The use of biometric based, Voiceprint is a safe & a secure method for authenticating an individual"s identity that unlike passwords or token, these characteristics of voice cannot be stolen, duplicated or forgotten [10] [11]. In recent years, a good amount of work has been contributed to English & other Indian languages; out of these Gujarati language has the least amount of work [14].…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction of Isolated Gujarati Digits with Mel Frequency Cepstral Coefficients (MFCCs)

Prajapati¹,

Patel²

2017

IJCA

View full text Add to dashboard Cite

The aim of this paper is to present feature extraction method of Gujarati isolated digit for speaker identification using MelFrequency Cepstral Coefficient (MFCC). The objective of MFCC is to extract features that are present in speech signal. That produces Mel-coefficients of speech data which helps in representing speaker specific characteristics, thus this technique is one of the best technique for feature extraction especially for automatic speech & speaker recognition system. This can offer better security than keypad input system at the ATM, cashless system, mobile password, etc. The proposed approach helps to implement the speaker identification system. Where dataset of Gujarati numeral (0 to 10) was recorded from different speakers from different age groups. This paper presents approach for extracting features from the speech signal of spoken words using the Mel-Scale Frequency Cepstral Coefficients. All this implementation is built in MATLAB environment. The result describes how it transform the input waveform into a sequence of acoustic feature vectors.

show abstract

Speaker independent continuous speech and isolated digit recognition using VQ and HMM

Cited by 22 publications

References 8 publications

Isolated Words Recognition Using Mfcc, LPC and Neural Network

Isolated Words Recognition Using Mfcc, LPC and Neural Network

Smart Voice Assistant for Library System

Feature Extraction of Isolated Gujarati Digits with Mel Frequency Cepstral Coefficients (MFCCs)

Contact Info

Product

Resources

About