The NISQA-TTS model weights can be used to estimate the Naturalness of synthetic speech generated by a Voice Conversion or Text-To-Speech system (Siri, Alexa, etc.). NISQA can be used to train new ...
Repository Summary Field Details Project type Deep learning image classification experiment Datasets Fashion-MNIST, CIFAR-10 Models Dense MLP baselines, CNN baselines Framework TensorFlow / Keras ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results