Optimizing Audio-Visual Speech Enhancement Using Multi-Level Distortion Measures for Audio-Visual Speech Recognition

H Chen, Q Wang, J Du, BC Yin, J Pan… - … /ACM Transactions on …, 2024 - ieeexplore.ieee.org
A multi-level distortion measure (MLDM) is proposed as an objective to optimize deep
neural network-based speech enhancement (SE) in both audio-only and audio-visual …

Development and Practical Applications of Computational Intelligence Technology

Y Matsuzaka, R Yashiro - BioMedInformatics, 2024 - mdpi.com
Computational intelligence (CI) uses applied computational methods for problem-solving
inspired by the behavior of humans and animals. Biological systems are used to construct …

Delineating Indic Transliteration: Develo** A Robust Model for Accurate Cross-Script Conversion

A Shukla, P Agrawal, S Jain - 2024 IEEE International Students' …, 2024 - ieeexplore.ieee.org
The aim of this study was to develop a reliable model of text change between two writing
systems." नमस्ते"(meaning" Hello") can be transliterated into Latin alphabet as" namaste" …

MATra: A Multilingual Attentive Transliteration System for Indian Scripts

Y Raj, B Laddagiri - arxiv preprint arxiv:2208.10801, 2022 - arxiv.org
Transliteration is a task in the domain of NLP where the output word is a similar-sounding
word written using the letters of any foreign language. Today this system has been …

Advancements in Handwriting Recognition: Deep Learning Techniques Applied to Kannada Language

HS Jayanna, BG Nagaraja, GT Yadava… - … on Smart Systems …, 2024 - ieeexplore.ieee.org
Numerous applications use handwriting recognition, such as optical character recognition,
document analysis, and automated form generation. Computer vision and machine learning …

[PDF][PDF] DGSRN: Noise-Robust Speech Recognition Method with Dual-Path Gated Spectral Refinement Network

W Wang, S Mo, L Dong, Z Yu, J Guo… - Proc. Interspeech …, 2024 - isca-archive.org
The advancements in speech recognition have led to significant progress in predicting clean
speech. However, challenges persist in real-world noisy environments. Addressing issues …

Improving Noise Robustness of Automatic Speech Recognition Based on a Parallel Adapter Model with Near-Identity Initialization

T Osaki, Y Sudo, K Itoyama, K Nishida… - … Conference on Industrial …, 2024 - Springer
This paper proposes the parallel adapter model (PAM) to improve the noise-robustness of
automatic speech recognition (ASR) systems with a small amount of retraining. The …

Review of Automatic Speech Recognition Systems for Ukrainian and English Language

A Dumyn, S Fedushko, Y Syerov - Data-Centric Business and Applications …, 2024 - Springer
Automatic speech recognition systems are highly regarded today since they can improve
inclusivity, streamline business communications, etc. This page overviews the most recent …

Correlated Multi-Level Speech Enhancement for Robust Real-World ASR Applications Using Mask-Waveform-Feature Optimization

H Chen, J Du, Z Wang, C Wang, Y Ren… - 2023 Asia Pacific …, 2023 - ieeexplore.ieee.org
Our proposed correlated multi-level optimization approach enhances speech recognition
performance for high-performance acoustic models in real-world applications. By combining …