Search Results for author:
Found 8 papers, 5 papers with code
CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment
Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing.
Self-Supervised Learning for Speech Enhancement through Synthesis
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction.
Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
Using weight pruning, we show that we are able to compress an already compact model's memory footprint by a factor of 42x from 3. 7MB to 87kB while only losing 0. 1 dB SDR in performance.
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids
Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs).
Neural Wavetable: a playable wavetable synthesizer using neural networks
We present Neural Wavetable, a proof-of-concept wavetable synthesizer that uses neural networks to generate playable wavetables.
MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
The three models, which differ in the underlying assumptions and accordingly the network architectures, are referred to as the jamming model, the composer model and the hybrid model.
Revisiting the problem of audio-based hit song prediction using convolutional neural networks
Being able to predict whether a song can be a hit has impor- tant applications in the music industry.
MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
We conduct a user study to compare the melody of eight-bar long generated by MidiNet and by Google's MelodyRNN models, each time using the same priming melody.
