Speech Feature Extraction for Gender Recognition

Pahwa, Anjali; Aggarwal, Gaurav

doi:10.5815/ijigsp.2016.09.03

Cited by 36 publications

(26 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…x is the value of the ith sample and  is the preemphasis coefficient. The value of α used in this experiment is 0.9, which is the same value used in [3,19]. This procedure is used to spectrally flatten the speech signal causing the perseverance of high-frequency components of the samples.…”

Section: A Pre-processingmentioning

confidence: 99%

Optimizing Parameters of Automatic Speech Segmentation into Syllable Units

Karim¹,

Suyanto²

2019

IJISA

View full text Add to dashboard Cite

An automatic speech segmentation into syllable is an important task in a modern syllable-based speech recognition. It is generally developed using a time-domain energy-based feature and a static threshold to detect a syllable boundary. The main problem is the fixed threshold should be defined exhaustively to get a high generalized accuracy. In this paper, an optimization method is proposed to adaptively find the best threshold. It optimizes the parameters of syllable speech segmentation and exploits two post-processing methods: iterative-splitting and iterative-assimilation. The optimization is carried out using three independent genetic algorithms (GAs) for three processes: boundary detection, iterative-splitting, and iterative-assimilation. Testing to an Indonesian speech dataset of 110 utterances shows that the proposed iterative-splitting with optimum parameters reduce deletion errors more than the commonly used non-iterative-splitting. The optimized iterative-assimilation is capable of removing more insertions, without over-merging, than the common noniterative-assimilation. The sequential combination of optimized iterative-splitting and optimized iterativeassimilation gives the highest accuracy with the lowest deletion and insertion errors.

show abstract

Section: A Pre-processingmentioning

confidence: 99%

Optimizing Parameters of Automatic Speech Segmentation into Syllable Units

Karim¹,

Suyanto²

2019

IJISA

View full text Add to dashboard Cite

show abstract

“…The speech analyzer uses Feature Extraction process to remove the background noise from the signals and retain the words that have been spoken into the microphone as shown in Fig. 4 [14].…”

Section: Step 3: Removal Of the Background Noisementioning

confidence: 99%

Evaluation Framework for Disabled Students based on Speech Recognition Technology

Pal¹,

Bhowmick²

2017

IJMECS

View full text Add to dashboard Cite

This paper intends to develop an evaluation framework for the students with disabilities based on speech recognition technology. Education is the most significant ingredient in the development and empowerment of individuals. Till the last decade, education was provided to the persons with disabilities in segregated school settings or "special schools". But in the recent years, there has been a great shift in societal attitude towards disabled students globally. The calls for "integration" of all students, disabled students and nondisabled students into the mainstream classroom environments have gathered momentum worldwide. In the pre-existing frameworks, the disabled students faced great difficulty while interacting with the system. The prime objective of our proposed framework is to provide a user-friendly and interactive environment that gives equal opportunities to all the students being evaluated. The utilization of speech recognition technology would lead to the elimination of all misinterpretations arising due to the human scribe or mediator and would enhance the ability of the disabled students to keep pace with the other students.

show abstract

“…GR can, for example, be achieved using low frequency data from the outline of a human face [4][5][6][7] ; kinematic data from gait analysis 3,8 ; skin texture 9 ; keystroke 10 ; voice; [11][12][13] and speech. [14][15][16][17][18] Recently some group of researchers worked on Parkinson's disease detection and GR using the deep network including pooling and feature extraction methods, to improve on the existing methods on GR. For instance, Tuncer and Dogan 19,20 and Yaman et al 21 worked on Parkinson's disease and gender detection.…”

Section: Introductionmentioning

confidence: 99%

“…Studies have shown that audio features such as the long-term structure of the audio spectrum, 35 Mel Frequency Cepstral Coefficient (MFCC), 36,37 its derivatives and transformations, 11,16,17,38,39 and Perceptual Linear Predictive, 36,37 are useful for gender classification and emotion recognition. Acoustic and prosodic features of speech 14,15,25 are other techniques that have been used for this classification and recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, some of the core visual biometric technologies initially built for person identification have demonstrated the ability to differentiate between genders, with reliable precision. GR can, for example, be achieved using low frequency data from the outline of a human face 4‐7 ; kinematic data from gait analysis 3,8 ; skin texture 9 ; keystroke 10 ; voice; 11‐13 and speech 14‐18 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laughter signature, a new approach to gender recognition

Folorunso

Popoola

Asaolu

2020

Engineering Reports

View full text Add to dashboard Cite

Gender Recognition (GR) is the process of identifying gender difference by extracting and evaluating features from data existing as images, video, audio, text, and other signals. The task of GR has been achieved using face, keystroke, gait, and speech features. "Laughter" with its intrinsic usefulness for this task is yet to be explored. Laughter is an important paralinguistic feature in human communication. It can change the meaning of speech when triggered by some form of arousal or amusement. Although, laughter can be "acted," but the human natural laughter is a spontaneous reflex response, which reasonably embeds some characteristic peculiarities of the individuals. The human brain has capacity to make this distinction. In this study, spontaneous laughter bouts of 123 volunteers (41 females and 82 males) were recorded. The Dynamic-Average of the Mel frequency Cepstral Coefficient (DA-MFCC) were generated and trained using two conventional and effective machine learning algorithms that have been employed in gender identification. These algorithms are Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) classifiers. Overall accuracies of 87.65% and 86.91% were obtained with GMM and SVM respectively. Therefore, indicating the possibility of using laughter characteristics as signatures for distinguishing between male and female genders. For both classifiers, the use of DA-MFCC reasonably reduced training time. Some of the potential areas of applications of GR include security, health care, marketing, human machine interaction toward enhanced emotion recognition, automatic speaker recognition and forensics.

show abstract

Speech Feature Extraction for Gender Recognition

Cited by 36 publications

References 1 publication

Optimizing Parameters of Automatic Speech Segmentation into Syllable Units

Optimizing Parameters of Automatic Speech Segmentation into Syllable Units

Evaluation Framework for Disabled Students based on Speech Recognition Technology

Laughter signature, a new approach to gender recognition

Contact Info

Product

Resources

About