Search
148 articles for “speaking”
-
Performance of Speaker Recognition System in Mismatching Speaking Style
Abstract: Analysis of speaker recognition system under different speaking style and mismatch conditions is presented. Generally, in text independent speaker recognition system, the way of speaking style used remains the same in training and testing phase. Whisper speech is generally used quietly to convey secret information or to avoid disturbing others in quiet place, so hearing of speech is limited to nearby listener only. Source of excitation and vocal tractsystem contains …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 5, Issue 3, 2018 · pp. 58–65 Read article
-
Speaker Variations and Vocal Disguise
Abstract: The process of recognizing the speaker based on parameters like pitch, loudness and other acoustic attributes is called speaker recognition. Speaker recognition is considered to be challenging. The voice changing apps facilitating vocal disguise have further made this process even difficult. The voice changing apps can induce variations, some of these variations may be predominantly different, even though these apps can disguise a person’s voice, certain parameters may stay real …
Published in Research and Reviews: A Journal of Health Professions · Vol. 13, Issue 2, 2023 · pp. 15–19 Read article
-
Audio-Only Speaker Identification using Principal Component Analysis based Back-Propagation Learning Neural Network in Noisy Environment
Abstract: This paper introduces text dependent speaker identification system on Principal Component Analysis based Back-Propagation learning neural network which deals with detecting a particular speaker from a known populations under noisy environment. For audio pre-processing, ends point detection, silence parts removal, frame segmentation and windowing techniques have been used and wiener filter has been applied to remove the background noise from the audio speech utterances. To reduce the dimension of the …
Published in Current Trends in Signal Processing · Vol. 3, Issue 3, 2013 · pp. 1–10 Read article
-
Singing and Speaking Voice Characteristics of Trans MtF
Abstract: Compared to other developed countries, in India, the transgender community are often overlooked as a non-existent community. These individuals are considered cursed, punished and therefore are forced to remain completely uninvolved in important matters of the society. Among all of the existing problems already faced by this community, misidentification of their gender based on the voice is a matter of concern. Among this group, most of them are engaged in …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 6, Issue 3, 2019 · pp. 1–4 Read article
-
Speaker Segmentation Using Non Linear Energy Operator Based Variance Spectral Flux
Abstract: AbstractSpeaker segmentation is considered to be a process that attempts to find speaker segment boundaries in a given audio stream. It can be used in various applications of speaker diarization, speaker indexing, word count etc. Classification of speech and non-speech can be obtained by traditional method of variance spectral flux (VSF). In this paper, we investigate the new techniques to perform the speaker segmentation task for multiple speakers in one …
Published in Current Trends in Signal Processing · Vol. 7, Issue 3, 2017 · pp. 1–6 Read article
-
Speaker Identification using Hopfield Neural Network based Classifier
Abstract: The aim of this work is to enhance the performance of speaker identification using Hopfield neural network algorithm. Speech signals are collected from VALID Audio-Visual dataset and some speech signal pre-processing techniques are applied to process the speech to feed the Hopfield neural network algorithm. Filtering technique is applied to remove the noises from the speech signals. MFCC based standard speech feature extraction technique is used to extract the speech …
Published in Journal Of Network security · Vol. 3, Issue 2, 2015 · pp. 32–35 Read article
-
Principal Component Analysis Based Dominant Features Selection Method for Speaker Identification
Abstract: Cepstrum based features are mostly used in speaker identification. Mel-frequency cepstrum coefficients (MFCCs) and their statistical properties (skewness, kurtosis and standard deviation) are used in this paper for text-dependent speaker identification. Principal component analysis (PCA) is employed to select the dominant feature vector representing the speaker characteristics. Multi-layer neural network is used as the classification engine. There occurs the inter-speaker variation of speech length uttering the same word. The feature …
Published in Current Trends in Signal Processing · Vol. 1, Issue 1-3, 2025 · pp. 33–45 Read article
-
Speaker Recognition System Through Matlab
Abstract: This paper presents the work on the Speaker Recognition System through the MATLAB software. Speaker recognition means recognizing the person who is actually speaking rather than knowing what has been said. This system is widely used in banking, security systems, voice mail, etc. This paper presents three stages of the system, namely, the voice acquisition stage in which data (speech signal) is acquired from the speaker and is stored for …
Published in Current Trends in Signal Processing · Vol. 3, Issue 2, 2013 · pp. 26–29 Read article
-
Back-Propagation Neural Network Based Speaker Identification Under Noise Distortion
Abstract: The aim of this paper is to evaluate the performance of the proposed speaker identification system where Wiener filtering technique has been used to eliminate the background white Gaussian noises and linear discriminant analysis has been used to reduce the dimension of the speech features. Since the audio signal captures more environmental noises than other biometrics modalities, the main emphasis of this paper is to analyze the problem domains of …
Published in Trends in Electrical Engineering · Vol. 5, Issue 2, 2015 · pp. 1–6 Read article
-
Native Language Identification from Spoken Indian English
Abstract: Automatic speech recognition (ASR) systems that facilitate voice based search and information retrieval have gained importance recently. While the performance of ASR systems for Indian languages have improved in the recent past. They have yet to gain wide acceptability as much as the ASR systems for English spoken by Indians. Almost all Indians learn English as a second or third language. So, the phoneme set and the prosody of native …
Published in Trends in Electrical Engineering · Vol. 9, Issue 2, 2019 · pp. 1–6 Read article
-
Recent Developments in MEMS Speaker Technology
Abstract: A sizable market with respect to portable audio calls for greater demand in MEMS speaker technology and manufacturing. A proper selection of electrostatic/electromagnetic actuators in a MEMS speaker gives rise to improved electromechanical efficiency. Summarizing the most recent developments could help in understanding the current technology and its scope. In this paper, several design selections and various types of MEMS speakers which are integrated with necessary components and circuitry in …
Published in Journal of VLSI Design Tools and Technology · Vol. 11, Issue 1, 2021 · pp. 29–34 Read article
-
Exploiting Phase of Speech Signal for Speaker Recognition
Abstract: Abstract—Performance of speaker recognition system with feature based on temporal phase is presented in this paper. In the state of the art spectral feature, Mel Frequency Cepstal Coefficient (MFCC) only magnitude of the Fourier Transform of speech signal is considered while phase is ignored. The cepstral coefficients extracted from temporal phase (MFTPC) of speech signal are used as features for speaker recognition system. The performance of MFTPC feature is evaluated …
Published in Journal of Communication Engineering & Systems · Vol. 9, Issue 2, 2019 · pp. 81–87 Read article
-
The Contextual Effect of Vowels on Correct Production of Retroflex in Kannada Speaking Children with Speech Sound Disorder: A Case Study
Abstract: Contextual based interaction of speech sounds, coarticulation, is the main component of intelligible continuous speech. This interaction between speech sounds within and across the words is affected in children with speech sound disorders (SSD). Literature reports on certain contexts facilitating the production of different speech sounds. Thus, these contextual considerations are vital for the selection of target stimuli during articulation therapy for faster learning. As phonotactics and coarticulation are language …
Published in Research and Reviews : Journal of Computational Biology · Vol. 7, Issue 2, 2018 · pp. 46–66 Read article
-
Acoustic Cue for Stress Perception in Kannada Speaking Children
Abstract: The perception of prosody is necessary to understand the intent of a spoken utterance, especially to appreciate the intricacies of a language. Prosody or the supra-segmental component is made up of stress (accent), intonation and the rhythmic (timing) patterns of language. Stress indicates the most prominent syllable/word in an utterance. Literature suggests language-specific acoustic cues for stress perception. Hence the present study was aimed to determine the major acoustic correlate …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 9, Issue 3, 2019 · pp. 16–23 Read article
-
Voice Recognition Technique using Guassian Mixture Model
Abstract: This paper gives us some of the important information about the methods used for voice recognition system. Voice recognition is the identification of person with the help of characteristic of voice. Voice recognition has scope ranging from access control to forensics. In this system we are able to identify the speaker as well as verification of the speaker take place using feature extraction and feature matching technique using GMM. In …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 2, Issue 2, 2015 · pp. 12–15 Read article
-
Articulatory Error Analysis in Kannada Speaking Children with Hearing Impairment: An Exploratory Study
Abstract: Speech sound errors are common in children with hearing impairment even after extensive speech therapy. Studies investigating the articulatory characteristics of children using hearing aids are relatively less reported in Indian languages. This study examined the nature of speech sound errors in Kannada speaking children with hearing impairment in comparison with age matched normal hearing peers. A detailed articulatory analysis was carried out from recorded speech samples. Research comparing articulatory …
Published in Research and Reviews: A Journal of Health Professions · Vol. 14, Issue 1, 2024 · pp. 47–57 Read article
-
Optimized Residual Neural Network for Audio Spoof Detection in Speaker Verification Systems
Abstract: The Automatic speaker verification system is a type of biometric technology that utilizes speech to determine if a person is an authentic user or not. Unfortunately, such systems can be susceptible to audio-spoofing attacks. The proposed work deals with this problem of Audio Spoofing by employing Residual Networks to determine if a voice signal is bonafide or not. A comparative study of Mel-frequency Cepstral coefficients (MFCC), Constant Q Cepstral Coefficients …
Published in Current Trends in Signal Processing · Vol. 12, Issue 2, 2022 · pp. 19–32 Read article
-
Neglect Analysis Using Semantic Picture Priming Paradigm among Hindi Speaking Developmental Dyslexics
Abstract: Introduction: Developmental dyslexia is a condition that is characterized by difficulties that mainly affect the ability of a child to read, write, calculate and spell. Developmental dyslexics may have neglected due to subtle weakness in a string of cortical areas on the bilateral dorsal pathway of the brain. Aim of the study: To analyze the presence of neglect in semantic picture priming paradigm among Hindi developmental dyslexics and typically developing …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 9, Issue 2, 2019 · pp. 39–45 Read article
-
SpeakEasy: Python’s Desktop Companion for Effortless Interaction
Abstract: With their ability to use natural language processing to enable hands-free technological engagement, voice assistants have become an indispensable aspect of modern living. This paper describes how to create a voice assistant with the Python programming language by utilizing its powerful libraries and frameworks for task automation, speech recognition, and natural language processing. The system architecture makes use of several Python modules, including PyAudio, NLTK (Natural Language Toolkit), and Speech …
Published in Current Trends in Signal Processing · Vol. 14, Issue 1, 2024 · pp. 15–23 Read article
-
Voice Recognition Technique Using Neural Network
Abstract: The scope of voice recognition ranges from access control to forensics. In a given environment the system will be able to recognize the correct speaker. This voice recognition technology can also recognize the voice based on their gender. This system uses the basic idea of Artificial Neural Network (ANN). Various techniques of ANN have been used in past to implement this system. This paper gives us some of the important …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 2, Issue 1, 2015 · pp. 15–18 Read article