Results 51 to 60 of about 938 (162)

Spoken term detection with Connectionist Temporal Classification: A novel hybrid CTC-DBN decoder [PDF]

2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010
This paper proposes a novel system for robust keyword detection in continuous speech. Our decoder is composed of a bidirectional Long Short-Term Memory recurrent neural network using a Connectionist Temporal Classification (CTC) output layer, and a Dynamic Bayesian Network (DBN).
Martin Wöllmer, Florian Eyben, Björn W. Schuller, Gerhard Rigoll   +3 more
openaire   +2 more sources

Inter‐Model Feature Fusion for Robust Low‐Resource Speech Recognition

Applied AI Letters, Volume 7, Issue 2, June 2026.
Our Self‐Supervised Feature Fusion (SSF‐FT) method enhances low‐resource speech recognition by adaptively combining features from self‐supervised models trained with Contrastive, Predictive, and Reconstruction objectives. This attention‐weighted ensemble delivers robust performance, particularly in acoustically challenging conditions, extending current
Ussen Kimanuka, Ciira wa Maina, Osman Büyük   +2 more
wiley   +1 more source

A deep neural network-based automatic mispronunciation detection in Bengali accented English speech

Discover Computing
Learning a second language, especially English, became necessary as globalisation started. One crucial component of language learning resources is computer-assisted pronunciation training, or CAPT.
Puja Bharati, Sabyasachi Chandra, Aniket Aitawade, Debolina Pramanik, Satya Prasad Gaddamedi, Shyamal Kumar Das Mandal   +5 more
doaj   +1 more source

A Linear Memory CTC-Based Algorithm for Text-to-Voice Alignment of Very Long Audio Recordings

Applied Sciences, 2023
Synchronisation of a voice recording with the corresponding text is a common task in speech and music processing, and is used in many practical applications (automatic subtitling, audio indexing, etc.).
Guillaume Doras, Yann Teytaut, Axel Roebel   +2 more
doaj   +1 more source

Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

CoRR, 2015
Final version: Kyuyeon Hwang and Wonyong Sung, "Sequence to Sequence Training of CTC-RNNs with Partial Windowing," Proceedings of The 33rd International Conference on Machine Learning, pp. 2178-2187, 2016.
Kyuyeon Hwang, Wonyong Sung
openaire   +2 more sources

A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

Applied AI Letters, Volume 7, Issue 2, June 2026.
This paper surveys deep reinforcement learning (DRL) for network intrusion detection, evaluating model efficiency, minority attack detection, and dataset imbalance. Findings show DRL achieves state‐of‐the‐art results on public datasets, sometimes surpassing traditional deep learning.
Wanrong Yang, Alberto Acuto, Yihang Zhou, Dominik Wojtczak   +3 more
wiley   +1 more source

Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks

Applied Sciences, 2021
The performance of automatic speech recognition (ASR) may be degraded when accented speech is recognized because the speech has some linguistic differences from standard speech.
Hyeong-Ju Na, Jeong-Sik Park
doaj   +1 more source

Probabilistic asr feature extraction applying context-sensitive connectionist temporal classification networks [PDF]

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
This paper proposes a novel automatic speech recognition (ASR) front-end that unites the principles of bidirectional Long Short-Term Memory (BLSTM), Connectionist Temporal Classification (CTC), and Bottleneck (BN) feature generation. BLSTM networks are known to produce better probabilistic ASR features than conventional multilayer perceptrons since ...
Martin Wöllmer, Björn W. Schuller, Gerhard Rigoll   +2 more
openaire   +1 more source

Quantum Activation Functions in Neural Networks: A Systematic Review of Approaches, Performance Impacts, and Practical Applications

Advanced Quantum Technologies, Volume 9, Issue 6, June 2026.
This review explores how quantum activation functions can contribute to the evolution of neural networks toward quantum computing. The results show that classical‐quantum hybrid architectures are being tested in some practical applications, while fully quantum models are still in the development phase. These functions represent an important step toward
Petterson Pina dos Santos, Mônica Silva de Oliveira, Adonney Allan de Oliveira Veras   +2 more
wiley   +1 more source

BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints

IEEE Access
We introduce BERT-NAR-BERT (BnB) – a pre-trained non-autoregressive sequence-to-sequence model, which employs BERT as the backbone for the encoder and decoder for natural language understanding and generation tasks.
Mohammad Golam Sohrab, Masaki Asada, Matiss Rikters, Makoto Miwa   +3 more
doaj   +1 more source