Results 101 to 110 of about 3,274,646 (190)

Text-Independent Phone-to-Audio Alignment Leveraging SSL (TIPAA-SSL) Pre-Trained Model Latent Representation and Knowledge Transfer

Acoustics
In this paper, we present a novel approach for text-independent phone-to-audio alignment based on phoneme recognition, representation learning and knowledge transfer.
Noé Tits, Prernna Bhatnagar, Thierry Dutoit   +2 more
doaj   +1 more source

Advances in Detecting RNA Modifications Using Direct RNA Nanopore Sequencing

Advanced Genetics, Volume 6, Issue 4, December 2025.
This review examines recent advances in Oxford Nanopore Technologies direct RNA sequencing, highlighting its expanding capacity to detect RNA modifications beyond m6A. It discusses computational frameworks and basecalling innovations that enable single‐nucleotide and single‐molecule resolution, explores co‐occurring modifications and their regulatory ...
Yaran Liu, Yang Li, Qiang Sun
wiley   +1 more source

New Techniques in Neural Networks Training - Connectionist Temporal Classification

, 2017
This bachelor’s thesis deals with neural network and their use in speech recognition. Firstly,there is some theory about speech recognition, afterwards we show theory around neural networks in connection with connectionist temporal classification ...
Gajdár, Matúš
core  

A Statistically Validated and Decoding-Aware CNN–Transformer–CTC Framework for Multi-Font Printed Arabic Word Recognition

Applied Sciences
Printed Arabic Optical Character Recognition (OCR) remains challenging due to complex glyph morphology, typographic variability, and sensitivity to Unicode-preserved evaluation protocols. This work introduces a methodology that explicitly treats decoding
Abderrahime Tabzaoui, Loqman Chakir
doaj   +1 more source

Audio Tagging With Connectionist Temporal Classification Model Using Sequentially Labelled Data

, 2019
Audio tagging aims to predict one or several labels in an audio clip. Many previous works use weakly labelled data (WLD) for audio tagging, where only presence or absence of sound events is known, but the order of sound events is unknown. To use the order information of sound events, we propose sequential labelled data (SLD), where both the presence or
Yuanbo Hou, Qiuqiang Kong, Shengchen Li
openaire   +2 more sources

Connectionist Inference Models [PDF]

, 2001
The performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform ...
Browne, Antony, Sun, Ron
core  

Speech Recognition for Air Traffic Control Utilizing a Multi-Head State-Space Model and Transfer Learning

Aerospace
In the present study, a novel end-to-end automatic speech recognition (ASR) framework, namely, ResNeXt-Mssm-CTC, has been developed for air traffic control (ATC) systems.
Haijun Liang, Hanwen Chang, Jianguo Kong
doaj   +1 more source

An Attention-Based Convolutional Recurrent Neural Networks for Scene Text Recognition

IEEE Access
Text recognition is critical in various domains, including driving assistance, handwriting recognition, and aiding the visually impaired. In recent years, deep learning-based methods have demonstrated outstanding performance in Scene Text Recognition ...
Adil Abdullah Abdulhussein Alshawi, Jafar Tanha, Mohammad Ali Balafar   +2 more
doaj   +1 more source

An Input-synchronous Blockwise Decoding Algorithm for CTC-AED Speech Recognition

Информатика и автоматизация
Automatic speech recognition (ASR) systems for real-life scenarios are required to process audio streams of arbitrary length with stable accuracy under limited computational resources.
Iurii Lezhenin, Natalia Bogach
doaj   +1 more source

Deep Multilevel Cascade Residual Recurrent Framework (MCRR) for Sheet Music Recognition

IEEE Access
Sheet music recognition is a vital technology aimed at converting printed or handwritten musical scores into digital or machine-readable formats.
Ping Yu, Hailing Chen
doaj   +1 more source