Search Results for author:
Found 20 papers, 7 papers with code
Detecting Out-of-Distribution Examples with Gram Matrices
We find that characterizing activity patterns by Gram matrices and identifying anomalies in Gram matrix values can yield high OOD detection rates.
VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations
This paper introduces the VISLA (Variance and Invariance to Semantic and Lexical Alterations) benchmark, designed to evaluate the semantic and lexical understanding of language models.
Test-Time Training for Depression Detection
Previous works on depression detection use datasets collected in similar environments to train and test the models.
Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
We propose Stochastic Control Guidance (SCG), a novel guidance method that only requires forward evaluation of rule functions that can work with pre-trained diffusion models in a plug-and-play way, thus achieving training-free guidance for non-differentiable rules for the first time.
SynthScribe: Deep Multimodal Tools for Synthesizer Sound Retrieval and Exploration
This is achieved with three main features: a multimodal search engine for a large library of synthesizer sounds; a user centered genetic algorithm by which completely new sounds can be created and selected given the users preferences; a sound editing support feature which highlights and gives examples for key control parameters with respect to a text or audio based query.
Test-Time Training for Speech
In this paper, we study the application of Test-Time Training (TTT) as a solution to handling distribution shifts in speech applications.
Training Diffusion Classifiers with Denoising Assistance
Score-matching and diffusion models have emerged as state-of-the-art generative models for both conditional and unconditional generation.
Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models
Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts.
Echofilter: A Deep Learning Segmentation Model Improves the Automation, Standardization, and Timeliness for Post-Processing Echosounder Data in Tidal Energy Streams
Application of a single conventional algorithm to identify the depth-of-penetration of entrained air is insufficient for a boundary that is discontinuous, depth-dynamic, porous, and varies with tidal flow speed.
LogAvgExp Provides a Principled and Performant Global Pooling Operator
We seek to improve the pooling operation in neural networks, by applying a more theoretically justified operator.
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
Consequently, we construct efficient approximations named $\text{AND}_\text{AIL}$ (the AND operator Approximate for Independent Logits), $\text{OR}_\text{AIL}$, and $\text{XNOR}_\text{AIL}$, which utilize only comparison and addition operations, have well-behaved gradients, and can be deployed as activation functions in neural networks.
Musical Speech: A Transformer-based Composition Tool
In this paper, we propose a new compositional tool that will generate a musical outline of speech recorded/provided by the user for use as a musical building block in their compositions.
Significance of Speaker Embeddings and Temporal Context for Depression Detection
In this work, we analyze the significance of speaker embeddings for the task of depression detection from speech.
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates.
Ranked #13 on
Out-of-Distribution Detection
on CIFAR-10 vs CIFAR-100
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Zero-Shot Out-of-Distribution Detection with Feature Correlations
We find that characterizing activity patterns by feature correlations and identifying anomalies in pairwise feature correlation values can yield high OOD detection rates.
Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Performance RNN is a machine-learning system designed primarily for the generation of solo piano performances using an event-based (rather than audio) representation.
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
In this work, we address the problem of musical timbre transfer, where the goal is to manipulate the timbre of a sound sample from one instrument to match another instrument while preserving other musical content, such as pitch, rhythm, and loudness.
This Time with Feeling: Learning Expressive Musical Performance
Music generation has generally been focused on either creating scores or interpreting them.
Onsets and Frames: Dual-Objective Piano Transcription
We advance the state of the art in polyphonic piano music transcription by using a deep convolutional and recurrent neural network which is trained to jointly predict onsets and frames.
Learning and Evaluating Musical Features with Deep Autoencoders
In this work we describe and evaluate methods to learn musical embeddings.
