Tag: speech processing

AdaptoNet achieved 99 percent accuracy on a 101-speaker speech dataset and demonstrated robust generalization on the AMI Meeting Corpus using ...

A new open-access study reports an AI and IoT-based system that classifies college spoken English performance with 95.47 percent accuracy ...

A comparative study found that GAN-based augmentation of speech or cepstrogram images improved Parkinson's dysarthria severity classification, with relative performance ...

An EML-CNN combining dense convolutional blocks, gated recurrent units and attention achieved speaker-identification accuracies above 96% across three benchmark datasets.

A Hungarian study published in Science shows that dog brains segment continuous speech into words using a consonant bias previously ...

A new multimodal deep learning framework fuses Log-Mel spectrograms and BERT embeddings through self-attention to automatically score spoken English fluency ...

A new survey in Artificial Intelligence Review unifies the four major attack vectors against voice authentication, finding that audio deepfakes ...