Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as WaveNet and SampleRNN suffer from prohibitive training and inference times because they are based on autoregressive models that generate audio samples one at a time at a rate of 16kHz. In this work, we study the more computationally efficient alternative of generating the waveform frame-by-frame with large strides. We present a lightweight neural audio synthesizer for the original task of generating musical notes given desired instrument, pitch and velocity. Our model is trained end-to-end to generate notes from nearly 1000 instruments with a single decoder, thanks to a new loss function that minimizes the distances between the log spectrograms of the generated and target waveforms. On the generalization task of synthesizing notes for pairs of pitch and instrument not seen during training, SING produces audio with significantly improved perceptual quality compared to a state-of-the-art autoencoder based on WaveNet as measured by a Mean Opinion Score (MOS), and is about 32 times faster for training and 2, 500 times faster for inference.

A bicycle wheel with guitar strings, a touch-operated synth, and the "Demon Box" were just a few of the new instruments on show at Georgia Tech's Guthman Musical Instrument Competition this weekend. An open-source, touch-operated synth built to resemble a puzzle piece and keep accessibility at the forefront. A pressure-sensitive surface allows for polyphonic synthesis that can be triggered by hands, feet, textured fabrics, or even Play-Doh. Brand new sounds floated through a concert hall at Georgia Tech this weekend, as the 28th annual Guthman Musical Instrument Competition showcased an array of new instruments from around the world--and crowned one champion. Ten finalists, chosen from candidates who built all kinds of new music-making devices, converged in Atlanta, Georgia, to present their instruments to a panel of judges.

Modern surgery has gone from long incisions to tiny cuts guided by robots and AI. In the process, however, surgeons have lost something vital: the chance to feel inside the body directly. Without palpation, it becomes harder to detect tissue abnormalities during an operation. A group of surgeons and engineers across Europe is now trying to bring back this vital aspect of surgery. Working within an EU-funded research collaboration called PALPABLE, they are developing a soft robotic "fingertip" that can sense how firm or soft tissue is during minimally invasive and robotic surgery.

From reducing dementia to speeding up recovery after surgery, music is more powerful than you knew. Listening to music can help your brain, research suggests. Breakthroughs, discoveries, and DIY tips sent six days a week. The oldest known musical instruments-- flutes carved from bones --are over 40,000 years old . And humans were likely making music before that, based on fossils showing our ancestors had the ability to sing over 530,000 years ago.

We propose nonparametric identification and semiparametric estimation of joint potential outcome distributions in the presence of confounding. First, in settings with observed confounding, we derive tighter, covariate-informed bounds on the joint distribution by leveraging conditional copulas. To overcome the non-differentiability of bounding min/max operators, we establish the asymptotic properties for both a direct estimator with polynomial margin condition and a smooth approximation with log-sum-exp operator, facilitating valid inference for individual-level effects under the canonical rank-preserving assumption. Second, we tackle the challenge of unmeasured confounding by introducing a causal representation learning framework. By utilizing instrumental variables, we prove the nonparametric identifiability of the latent confounding subspace under injectivity and completeness conditions. We develop a ``triple machine learning" estimator that employs cross-fitting scheme to sequentially handle the learned representation, nuisance parameters, and target functional. We characterize the asymptotic distribution with variance inflation induced by representation learning error, and provide conditions for semiparametric efficiency. We also propose a practical VAE-based algorithm for confounding representation learning. Simulations and real-world analysis validate the effectiveness of proposed methods. By bridging classical semiparametric theory with modern representation learning, this work provides a robust statistical foundation for distributional and counterfactual inference in complex causal systems.

Accurately predicting conditional average treatment effects (CA TEs) is crucial in personalized medicine and digital platform analytics.

However, most methods rely heavily on music domain knowledge.

Neural Information Processing Systems http://nips.cc/