In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable-$Q$ Transform (VQT) and predicts pitch distributions. The neural network is designed to be equivariant to translations, notably thanks to a Toeplitz fully-connected layer. In addition, we construct pitch-shifted pairs by translating and cropping the VQT frames and train our model with a novel class-based transposition-equivariant objective, eliminating the need for annotated data. Thanks to this architecture and training objective, our model achieves remarkable performances while being very lightweight ($130$k parameters). Evaluations on music and speech datasets (MIR-1K, MDB-stem-synth, and PTDB) demonstrate that PESTO not only outperforms self-supervised baselines but also competes with supervised methods, exhibiting superior cross-dataset generalization. Finally, we enhance PESTO's practical utility by developing a streamable VQT implementation using cached convolutions. Combined with our model's low latency (less than 10 ms) and minimal parameter count, this makes PESTO particularly suitable for real-time applications.

Sea Life Melbourne Aquarium celebrates their star penguin, Pesto, who weighs a whopping 49 pounds. PENGUIN-INSPIRED ROBOT EXPLORES SEA USING AI Pesto weighs more than both his proud parents combined at a staggering 49 pounds. His parents, Hudson and Tango, each weigh about 24 pounds. According to a statement from the Sea Life Melbourne Aquarium, Pesto is the heaviest chick the facility has ever had. His gender was announced to the world earlier this month when his keeper, Michaela Smale, "shovel[ed] away a mountain of fresh snow to unleash an avalanche of blue."

The geometric deep-learning method (PeSTo) used to predict protein binding interfaces. The amino acids involved in the protein binding interface are highlighted in red. Proteins are essential to the biological functions of most living organisms. They have evolved to interact with other proteins, nucleic acids, lipids etc., and all of those interactions form large, "supra-molecular" complexes. This means that understanding protein interactions is crucial for understanding many cellular processes.

NLP applications for code-mixed (CM) or mix-lingual text have gained a significant momentum recently, the main reason being the prevalence of language mixing in social media communications in multi-lingual societies like India, Mexico, Europe, parts of USA etc. Word embeddings are basic build-ing blocks of any NLP system today, yet, word embedding for CM languages is an unexplored territory. The major bottleneck for CM word embeddings is switching points, where the language switches. These locations lack in contextually and statistical systems fail to model this phenomena due to high variance in the seen examples. In this paper we present our initial observations on applying switching point based positional encoding techniques for CM language, specifically Hinglish (Hindi - English). Results are only marginally better than SOTA, but it is evident that positional encoding could bean effective way to train position sensitive language models for CM text.