Flash-SemiCRF enables exact semi-CRF inference on long sequences by evaluating edge potentials from compact prefix sums and streaming the forward-backward pass while preserving exact gradients.
An overview of voice conversion systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Hierarchical seq2seq model for parallel voice conversion pretrained as autoencoder on single-speaker data then adapted to limited multispeaker data, using mel spectrograms converted via wavenet vocoder.
CNN-Transformer hybrid reaches 98.1% accuracy on Arabic SER using EYASE and BAVED datasets, outperforming CNN-LSTM and fine-tuned wav2vec 2.0.
citing papers explorer
-
Streaming Structured Inference with Flash-SemiCRF
Flash-SemiCRF enables exact semi-CRF inference on long sequences by evaluating edge potentials from compact prefix sums and streaming the forward-backward pass while preserving exact gradients.
-
Hierarchical Sequence to Sequence Voice Conversion with Limited Data
Hierarchical seq2seq model for parallel voice conversion pretrained as autoencoder on single-speaker data then adapted to limited multispeaker data, using mel spectrograms converted via wavenet vocoder.
-
Towards Robust Arabic Speech Emotion Recognition with Deep Learning
CNN-Transformer hybrid reaches 98.1% accuracy on Arabic SER using EYASE and BAVED datasets, outperforming CNN-LSTM and fine-tuned wav2vec 2.0.