Audio Super Resolution using Neural Networks
This provides a practical solution for improving audio quality in applications like telephony and compression, though it is incremental as it adapts existing image super-resolution methods to audio.
The paper tackles audio super-resolution by using deep convolutional neural networks to increase sampling rates, achieving performance that outperforms baselines on speech and music benchmarks at upscaling ratios of 2x, 4x, and 6x.
We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time, it predicts missing samples within a low-resolution signal in an interpolation process similar to image super-resolution. Our method is simple and does not involve specialized audio processing techniques; in our experiments, it outperforms baselines on standard speech and music benchmarks at upscaling ratios of 2x, 4x, and 6x. The method has practical applications in telephony, compression, and text-to-speech generation; it demonstrates the effectiveness of feed-forward convolutional architectures on an audio generation task.