[HTML][HTML] A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications
Data scarcity is a major challenge when training deep learning (DL) models. DL demands a
large amount of data to achieve exceptional performance. Unfortunately, many applications …
large amount of data to achieve exceptional performance. Unfortunately, many applications …
Unsupervised domain adaptation for speech recognition via uncertainty driven self-training
The performance of automatic speech recognition (ASR) systems typically degrades
significantly when the training and test data domains are mismatched. In this paper, we …
significantly when the training and test data domains are mismatched. In this paper, we …
Momentum pseudo-labeling: Semi-supervised asr with continuously improving pseudo-labels
End-to-end automatic speech recognition (ASR) has become a popular alternative to
traditional module-based systems, simplifying the model-building process with a single deep …
traditional module-based systems, simplifying the model-building process with a single deep …
Modulation recognition using signal enhancement and multistage attention mechanism
Robustness against noise is critical for modulation recognition (MR) approaches deployed
in real-world communication systems. In MR systems, a corrupted signal is normally …
in real-world communication systems. In MR systems, a corrupted signal is normally …
Momentum pseudo-labeling for semi-supervised speech recognition
Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech
recognition (ASR), where a base model is self-trained with pseudo-labels generated from …
recognition (ASR), where a base model is self-trained with pseudo-labels generated from …
Alternative pseudo-labeling for semi-supervised automatic speech recognition
When labeled data is insufficient, pseudo-labeling based semi-supervised learning can
significantly improve the performance of automatic speech recognition. However, pseudo …
significantly improve the performance of automatic speech recognition. However, pseudo …
CTC variations through new WFST topologies
This paper presents novel Weighted Finite-State Transducer (WFST) topologies to
implement Connectionist Temporal Classification (CTC)-like algorithms for automatic …
implement Connectionist Temporal Classification (CTC)-like algorithms for automatic …
Multi-channel attentive feature fusion for radio frequency fingerprinting
Radio frequency (RF) fingerprinting is a promising device authentication technique for
securing the Internet of Things. It exploits the intrinsic and unique hardware impairments of …
securing the Internet of Things. It exploits the intrinsic and unique hardware impairments of …
A novel self-training approach for low-resource speech recognition
In this paper, we propose a self-training approach for automatic speech recognition (ASR)
for low-resource settings. While self-training approaches have been extensively developed …
for low-resource settings. While self-training approaches have been extensively developed …
Bayes risk ctc: Controllable ctc alignment in sequence-to-sequence tasks
Sequence-to-Sequence (seq2seq) tasks transcribe the input sequence to a target sequence.
The Connectionist Temporal Classification (CTC) criterion is widely used in multiple …
The Connectionist Temporal Classification (CTC) criterion is widely used in multiple …