Accent based speech recognition: A critical overview

Thandil, Rizwana Kallooravi; Basheer, K. P. Mohamed

doi:10.26637/mjm0804/0070

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(a) Specific subfields. (Thandil & Basheer, 2020) divided the development of speech recognition technology into four stages: the embryonic stage (1985)(1986)(1987)(1988)(1989)(1990)(1991)(1992)(1993), the rapid development stage (1993)(1994)(1995)(1996)(1997)(1998)(1999)(2000)(2001), the mature stage (2001)(2002)(2003)(2004)(2005)(2006)(2007), and the commercial application stage (since 2007). (Zhou, 2018) To sum up, the previous division of AI industry development stage mostly focused on a specific subfield or a non-systematical set.…”

Section: Division and Judgment Of The Ai Industry Development Stagesmentioning

confidence: 99%

“…(a) Specific subfields. (Thandil & Basheer, 2020) divided the development of speech recognition technology into four stages: the embryonic stage (1985–1993), the rapid development stage (1993–2001), the mature stage (2001–2007), and the commercial application stage (since 2007). (Zhou, 2018) divided the development stage of machine learning into the shallow learning stage (1943–2006), the deep learning stage (2006–2011), and the outbreak stage (since 2012).…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Correlation Monitoring Method and model of Science-Technology-Industry in the AI Field: A Case of the Neural Network

et al. 2022

View full text Add to dashboard Cite

This article aims to analyze the correlation status and development trend among science, technology and industry in the Artificial Intelligence (AI) subfield. First, it constructs the classification system and retrieval strategy for the AI subfield, and performs data cleaning and data finishing. Second, it designs the criteria and judgment method of the Industry Development Stages (IDS) in the AI subfield with the Delphi survey method. Third, it designs the monitoring method and model of the Science-Technology-Industry (STI) correlation with the methods of scientometrics and clustering, which involves three dimensions: science and IDS, technology and IDS, science & technology clustering and IDS; especially the monitoring with the global and national perspectives. Finally, it conducts empirical application in the field of neural network. The results illustrate that the correlation monitoring method can be conducive to grasp accurately the development opportunity and trend, the advantage subfield, and the development status of Science and Technology (S&T) for the dominant countries. The United States leads the global development in the empirical field. The proposed correlation monitoring method in this article can also be applied in other fields.

show abstract

Section: Division and Judgment Of The Ai Industry Development Stagesmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Correlation Monitoring Method and model of Science-Technology-Industry in the AI Field: A Case of the Neural Network

et al. 2022

View full text Add to dashboard Cite

show abstract

CAPTuring Accents: An Approach to Personalize Pronunciation Training for Learners with Different L1 Backgrounds

Khaustova,

Pyshkin,

Khaustov

et al. 2023

Speech and Computer

View full text Add to dashboard Cite

Implementation of Machine Learning-Aided Speech Analysis for Speaker Accent Identification Applied to Audio Forensics

Mahesh

Raj

Nersisson

2022

Advances in Digital Crime, Forensics, and Cyber Terrorism

View full text Add to dashboard Cite

Accent recognition as a subset of speech recognition is crucial in audio forensics as it provides the authenticity of the speech that can be presented to the judicature as evidence. The challenge here is to design a speaker accent identifying system that can provide significant information to match with the standards of the court of justice. This process requires robust descriptors to represent speech signal with good discrimination ability. This chapter proposes to use Mel Frequency Cepstral Coefficients to identify and represent the human utterances by transforming the frequency from normal scale to Mel scale. The work utilized support vector machine, k nearest neighbors, XG boost, linear discriminant analysis, quadratic discriminant analysis, and decision tree algorithms to recognize the accent of the speaker. The experiment conducted on the accent recognition dataset demonstrated the ability of Mel Frequency Cepstral Coefficients and kNN classifier in identifying and discriminating six accents belonging to different speakers with better accuracy.

show abstract

Accent based speech recognition: A critical overview

Cited by 3 publications

References 32 publications

Correlation Monitoring Method and model of Science-Technology-Industry in the AI Field: A Case of the Neural Network

Correlation Monitoring Method and model of Science-Technology-Industry in the AI Field: A Case of the Neural Network

CAPTuring Accents: An Approach to Personalize Pronunciation Training for Learners with Different L1 Backgrounds

Implementation of Machine Learning-Aided Speech Analysis for Speaker Accent Identification Applied to Audio Forensics

Contact Info

Product

Resources

About