DARF: A data-reduced FADE version for simulations of speech recognition thresholds with real hearing aids

Hülsmeier, David; Schädler, Marc René; Kollmeier, Birger

doi:10.1016/j.heares.2021.108217

Cited by 5 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A specific ASR called FADE, developed by Schädler, et al 34 , was designed to forecast human auditory performance in speech recognition tasks. This ASR is based on Gaussian mixture models and hidden Markov models (GMM-HMM) that simulates the human speech recognition process 35,36 . Unlike the off-the-shelf (standard) ASRs mentioned earlier, this particular system employs identical speech and noise stimuli for both training and testing purposes.…”

Section: Resultsmentioning

confidence: 99%

Global access to speech hearing tests

Polspoel,

Moore,

Swanepoel

et al. 2024

Preprint

View full text Add to dashboard Cite

Understanding speech in noisy settings is one of the biggest challenges for individuals with hearing loss. Traditional speech-in-noise tests play a crucial role in screening for and diagnosing hearing loss, but are resource-intensive to develop, limiting accessibility, particularly in low and middle-income countries. This four-part study introduces an innovative approach using artificial intelligence (AI) to automate the development of such tests. By leveraging text-to-speech (TTS) and automatic speech recognition (ASR) technologies, this approach significantly reduces the cost, time, and resources required for high-quality speech-in-noise testing accessible worldwide. The procedure, named “Aladdin” (Automatic LAnguage-independent Development of the Digits-In-Noise test), creates digits-in-noise (DIN) hearing tests through synthetic speech material and ASR-based level corrections to perceptually equalize the digits, demonstrating characteristics comparable to traditional tests. Notably, Aladdin provides a universal guideline for developing DIN tests across languages, addressing the challenge of comparing test results across variants. This approach, with its potential for broad application in audiology, represents a significant advancement in test development and offers a cost-effective and efficient enhancement to global screening and treatment for hearing loss.

show abstract

Section: Resultsmentioning

confidence: 99%

Global access to speech hearing tests

Polspoel,

Moore,

Swanepoel

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…By studying and analyzing the semantic differences of spoken English in different scenarios, Gla and other scholars put forward a new “point-to-point” ladder evaluation system of spoken English and verified the effectiveness of the speech recognition system in the process of different spoken English recognition through practice [ 11 ]. Aiming at the problem of high error rate in speech recognition technology, Hülsmeier et al, combined with multivariate screening strategy and mesh analysis method, proposed an environment fusion recognition method based on Internet of things intelligent algorithm [ 12 ].…”

Section: Related Workmentioning

confidence: 99%

Analysis Model of Spoken English Evaluation Algorithm Based on Intelligent Algorithm of Internet of Things

Xue

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the in-depth promotion of the national strategy for the integration of artificial intelligence technology and entity development, speech recognition processing technology, as an important medium of human-computer interaction, has received extensive attention and motivated research in industry and academia. However, the existing accurate speech recognition products are based on massive data platform, which has the problems of slow response and security risk, which makes it difficult for the existing speech recognition products to meet the application requirements for timely translation of speech with high response time and network security requirements under the condition of network instability and insecurity. Based on this, this paper studies the analysis model of oral English evaluation algorithm based on Internet of things intelligent algorithm in speech recognition technology. Firstly, based on the automatic machine learning and lightweight learning strategy, a lightweight technology of automatic speech recognition depth neural network adapted to the edge computing power is proposed. Secondly, the quantitative evaluation of Internet of things intelligent classification algorithm and big data analysis in this system is described. In the evaluation, the evaluation method of oral English characteristics is adopted. At the same time, the Internet of things intelligent classification algorithm and big data analysis strategy are used to evaluate the accuracy of oral English. Finally, the experimental results show that the oral English feature recognition system based on Internet of things intelligent classification algorithm and big data analysis has the advantages of good reliability, high intelligence, and strong ability to resist subjective factors, which proves the advantages of Internet of things intelligent classification algorithm and big data analysis in English feature recognition.

show abstract

ASR-based speech intelligibility prediction: A review

Karbasi

Kolossa

2022

Hearing Research

View full text Add to dashboard Cite

DARF: A data-reduced FADE version for simulations of speech recognition thresholds with real hearing aids

Cited by 5 publications

References 51 publications

Global access to speech hearing tests

Global access to speech hearing tests

Analysis Model of Spoken English Evaluation Algorithm Based on Intelligent Algorithm of Internet of Things

ASR-based speech intelligibility prediction: A review

Contact Info

Product

Resources

About