Computational intelligence in processing of speech acoustics: a survey

Singh, Amitoj; Kaur, Navkiran; Kukreja, Vinay; Kadyan, Virender; Kumar, Munish

doi:10.1007/s40747-022-00665-1

Cited by 11 publications

(5 citation statements)

References 284 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another critical challenge is the robustness of these systems in diverse conditions. Factors like background noise, the speaker's emotional state, and varied recording qualities significantly impact performance (Gheewalla, McClelland, & Furnham, 2021;A. Singh, Kaur, Kukreja, Kadyan, & Kumar, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluating the Efficacy of Traditional Machine Learning Models in Speaker Recognition: A Comparative Study Using the LibriSpeech Dataset

Airlangga

2024

Brilliance

View full text Add to dashboard Cite

The efficacy of machine learning models in speaker recognition tasks is critical for advancements in security systems, biometric authentication, and personalized user interfaces. This study provides a comparative analysis of three prominent machine learning models: Naive Bayes, Logistic Regression, and Gradient Boosting, using the LibriSpeech test-clean dataset—a corpus of read English speech from audiobooks designed for training and evaluating speech recognition systems. Mel-Frequency Cepstral Coefficients (MFCCs) were extracted as features from the audio samples to represent the power spectrum of the speakers’ voices. The models were evaluated based on precision, recall, F1-score, and accuracy to determine their performance in correctly identifying speakers. Results indicate that Logistic Regression outperformed the other models, achieving nearly perfect scores across all metrics, suggesting its superior capability for linear classification in high-dimensional spaces. Naive Bayes also demonstrated high efficiency and robustness, despite the inherent assumption of feature independence, while Gradient Boosting showed slightly lower performance, potentially due to model complexity and overfitting. The study underscores the potential of simpler machine learning models to achieve high accuracy in speaker recognition tasks, particularly where computational resources are limited. However, limitations such as the controlled nature of the dataset and the focus on a single feature type were noted, with recommendations for future research to include more diverse environmental conditions and feature sets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Evaluating the Efficacy of Traditional Machine Learning Models in Speaker Recognition: A Comparative Study Using the LibriSpeech Dataset

Airlangga

2024

Brilliance

View full text Add to dashboard Cite

show abstract

“…The accuracy of speech recognition systems still needs to be improved in noisy driving environments. Factors such as noise, speech variation, and in-vehicle sounds may interfere with the results of speech recognition, reducing the reliability of the system [6] . To solve this problem, researchers have proposed some new perspectives and approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning algorithms can be trained with large-scale data to automatically learn abstract features of speech and thus improve recognition accuracy [7]. In addition, researchers have explored ways to combine speech recognition with other sensor data, such as using microphone arrays and in-car cameras in the driving environment to improve the accuracy and stability of voice commands [6].…”

Section: Introductionmentioning

confidence: 99%

New perspective on human-computer interaction-based on speech recognition in driving

Xue

2024

ACE

View full text Add to dashboard Cite

With the popularity of smart driving and in-vehicle intelligent systems, speech recognition plays an important role in driving as a key link of human-computer interaction. However, although speech recognition systems have been widely used, their application inhuman-computer interaction still needs to be improved. The purpose of this paper is to examine or review the latest perspectives on speech recognition as part of human-computer interaction in driving. lt provides an in-depth understanding of the potential and future development of speech recognition in driving by exploring, among other things, new directions and features that can be improved. Through a comprehensive analysis of relevant literature and research results, this paper will provide an overview of the current state of speech recognition in human-computer interaction, point out the challenges and limitations that still exist in the driving environment, and focus on new perspectives on speech recognition in driving that may enable more highly accurate command recognition and natural conversational interaction to enhance the driving experience and safety through the use of advanced speech recognition technologies. Explore how technologies such as artificial intelligence and machine learning can be used to drive the development of speech recognition and address current challenges. ln addition, research advances in the areas of driving behavior analysis, emotion recognition, and personalized driving related to speech recognition will be explored. The review and analysis in this paper will provide valuable references and guidance for further research and development of speech recognition-based driving human-computer interaction systems.

show abstract

“…Translating texts from one language to another https://www.indjst.org/ is carried out using machine translation software. The blooming of Text-to-Speech (TTS) systems for Tamil languages has received extensive research (2,3) . An area of natural language processing stands at the point where languages and artificial intelligence meet.…”

Section: Introductionmentioning

confidence: 99%

Tamil Speech Synthesizer App for Android: Text Processing Module Enhancement

Arulprakash¹,

Synthiya²,

Vijila³

et al. 2023

IJST

View full text Add to dashboard Cite

Objectives: Designing dynamic computer systems that are effective, efficient, simple, and satisfying to use is becoming extremely important in this age of information and communication technology. Text to Speech or Speech Synthesis is one of the many methods being investigated by researchers to improve Human-Computer Interaction. The goal here is to improve the text processing component of the Tamil voice synthesizer by including a text normalizer and loan word identification that is efficient and reliable. Methods: Text normalization is conducted on unconstrained Tamil text to turn non-standard terms into common words to reduce confusing utterances during intermediate word processing. Loan/Native words in Tamil literature are detected to enhance the Tamil voice synthesizer system's pronunciation model. Findings: During normalization, non-standard Tamil words are replaced with standard ones to reduce ambiguous utterances during interim processing. A pronunciation model is built to improve the Tamil speech synthesizer system by identifying loan words in Tamil text. A syllable classifier is presented in this study, based on a decision list approach, which can handle various types of non-stationary sounds. Novelty: We also disclose a 'loan/native word classifier' based on multiple linear regressions that perform well even with small words of three syllables. Such sophisticated text processors are required in today's dominating Digital, Information-Communication Technology, and Human-Computer Interaction age.

show abstract

Computational intelligence in processing of speech acoustics: a survey

Cited by 11 publications

References 284 publications

Evaluating the Efficacy of Traditional Machine Learning Models in Speaker Recognition: A Comparative Study Using the LibriSpeech Dataset

Evaluating the Efficacy of Traditional Machine Learning Models in Speaker Recognition: A Comparative Study Using the LibriSpeech Dataset

New perspective on human-computer interaction-based on speech recognition in driving

Tamil Speech Synthesizer App for Android: Text Processing Module Enhancement

Contact Info

Product

Resources

About