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. In particular, we introduce distribution-shifts to the test datasets of standard speech-classification tasks -- for example, speaker-identification and emotion-detection -- and explore how Test-Time Training (TTT) can help adjust to the distribution-shift. In our experiments that include distribution shifts due to background noise and natural variations in speech such as gender and age, we identify some key-challenges with TTT including sensitivity to optimization hyperparameters (e.g., number of optimization steps and subset of parameters chosen for TTT) and scalability (e.g., as each example gets its own set of parameters, TTT is not scalable). Finally, we propose using BitFit -- a parameter-efficient fine-tuning algorithm proposed for text applications that only considers the bias parameters for fine-tuning -- as a solution to the aforementioned challenges and demonstrate that it is consistently more stable than fine-tuning all the parameters of the model.

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. Classifier-guided diffusion models are created by training a classifier on samples obtained from the forward-diffusion process (i.e., from data to noise). In this paper, we propose denoising-assisted (DA) classifiers wherein the diffusion classifier is trained using both noisy and denoised examples as simultaneous inputs to the model. We differentiate between denoising-assisted (DA) classifiers and noisy classifiers, which are diffusion classifiers that are only trained on noisy examples. Our experiments on Cifar10 and Imagenet show that DA-classifiers improve over noisy classifiers both quantitatively in terms of generalization to test data and qualitatively in terms of perceptually-aligned classifier-gradients and generative modeling metrics. Finally, we describe a semi-supervised framework for training diffusion classifiers and our experiments, that also include positive-unlabeled settings, demonstrate improved generalization of DA-classifiers over noisy classifiers.

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. However, crafting prompts that accurately capture the user's creative intent remains challenging. It often involves laborious trial-and-error procedures to ensure that the model interprets the prompts in alignment with the user's intention. To address the challenges, we present Promptify, an interactive system that supports prompt exploration and refinement for text-to-image generative models. Promptify utilizes a suggestion engine powered by large language models to help users quickly explore and craft diverse prompts. Our interface allows users to organize the generated images flexibly, and based on their preferences, Promptify suggests potential changes to the original prompt. This feedback loop enables users to iteratively refine their prompts and enhance desired features while avoiding unwanted ones. Our user study shows that Promptify effectively facilitates the text-to-image workflow and outperforms an existing baseline tool widely used for text-to-image generation.

Generative Extraction of Audio Classifiers for Speaker Identification

It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well studied is model extraction: a phenomenon in which the attacker attempts to steal a victim's model by training a surrogate model to mimic the decision boundaries of the victim model. Previous works have demonstrated the effectiveness of such an attack and its devastating consequences, but much of this work has been done primarily for image and text processing tasks. Our work is the first attempt to perform model extraction on {\em audio classification models}. We are motivated by an attacker whose goal is to mimic the behavior of the victim's model trained to identify a speaker. This is particularly problematic in security-sensitive domains such as biometric authentication. We find that prior model extraction techniques, where the attacker \textit{naively} uses a proxy dataset to attack a potential victim's model, fail. We therefore propose the use of a generative model to create a sufficiently large and diverse pool of synthetic attack queries. We find that our approach is able to extract a victim's model trained on \texttt{LibriSpeech} using queries synthesized with a proxy dataset based off of \texttt{VoxCeleb}; we achieve a test accuracy of 84.41\% with a budget of 3 million queries.

Echofilter: A Deep Learning Segmentation Model Improves the Automation, Standardization, and Timeliness for Post-Processing Echosounder Data in Tidal Energy Streams

Understanding the abundance and distribution of fish in tidal energy streams is important for assessing the risk presented by the introduction of tidal energy devices into the habitat. However, the impressive tidal currents that make sites favorable for tidal energy development are often highly turbulent and entrain air into the water, complicating the interpretation of echosounder data. The portion of the water column contaminated by returns from entrained air must be excluded from data used for biological analyses. Application of a single algorithm to identify the depth-of-penetration of entrained-air is insufficient for a boundary that is discontinuous, depth-dynamic, porous, and widely variable across the tidal flow speeds which can range from 0 to 5m/s. Using a case study at a tidal energy demonstration site in the Bay of Fundy, we describe the development and application of deep learning models that produce a pronounced, consistent, substantial, and measurable improvement of the automated detection of the extent to which entrained-air has penetrated the water column. Our model, Echofilter, was highly responsive to the dynamic range of turbulence conditions and sensitive to the fine-scale nuances in the boundary position, producing an entrained-air boundary line with an average error of 0.32m on mobile downfacing and 0.5-1.0m on stationary upfacing data. The model's annotations had a high level of agreement with the human segmentation (mobile downfacing Jaccard index: 98.8%; stationary upfacing: 93-95%). This resulted in a 50% reduction in the time required for manual edits compared to the time required to manually edit the line placed by currently available algorithms. Because of the improved initial automated placement, the implementation of the models generated a marked increase in the standardization and repeatability of line placement.

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. We demonstrate that LogSumExp provides a natural OR operator for logits. When one corrects for the number of elements inside the pooling operator, this becomes $\text{LogAvgExp} := \log(\text{mean}(\exp(x)))$. By introducing a single temperature parameter, LogAvgExp smoothly transitions from the max of its operands to the mean (found at the limiting cases $t \to 0^+$ and $t \to +\infty$). We experimentally tested LogAvgExp, both with and without a learnable temperature parameter, in a variety of deep neural network architectures for computer vision.

Logical Activation Functions: Logit-space equivalents of Boolean Operators

Neuronal representations within artificial neural networks are commonly understood as logits, representing the log-odds score of presence (versus absence) of features within the stimulus. Under this interpretation, we can derive the probability $P(x_0 \land x_1)$ that a pair of independent features are both present in the stimulus from their logits. By converting the resulting probability back into a logit, we obtain a logit-space equivalent of the AND operation. However, since this function involves taking multiple exponents and logarithms, it is not well suited to be directly used within neural networks. We thus constructed an efficient approximation named $\text{AND}_\text{AIL}$ (the AND operator Approximate for Independent Logits) utilizing only comparison and addition operations, which can be deployed as an activation function in neural networks. Like MaxOut, $\text{AND}_\text{AIL}$ is a generalization of ReLU to two-dimensions. Additionally, we constructed efficient approximations of the logit-space equivalents to the OR and XNOR operators. We deployed these new activation functions, both in isolation and in conjunction, and demonstrated their effectiveness on a variety of tasks including image classification, transfer learning, abstract reasoning, and compositional zero-shot learning.

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. The tool allows any user to use their own speech to generate musical material, while still being able to hear the direct connection between their recorded speech and the resulting music. The tool is built on our proposed pipeline. This pipeline begins with speech-based signal processing, after which some simple musical heuristics are applied, and finally these pre-processed signals are passed through Transformer models trained on new musical tasks. We illustrate the effectiveness of our pipeline -- which does not require a paired dataset for training -- through examples of music created by musicians making use of our tool.

Significance of Speaker Embeddings and Temporal Context for Depression Detection

Depression detection from speech has attracted a lot of attention in recent years. However, the significance of speaker-specific information in depression detection has not yet been explored. In this work, we analyze the significance of speaker embeddings for the task of depression detection from speech. Experimental results show that the speaker embeddings provide important cues to achieve state-of-the-art performance in depression detection. We also show that combining conventional OpenSMILE and COVAREP features, which carry complementary information, with speaker embeddings further improves the depression detection performance. The significance of temporal context in the training of deep learning models for depression detection is also analyzed in this paper.

Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices

When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and class predicted. We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates. We identify anomalies in the gram matrices by simply comparing each value with its respective range observed over the training data. Unlike many approaches, this can be used with any pre-trained softmax classifier and does not require access to OOD data for fine-tuning hyperparameters, nor does it require OOD access for inferring parameters. The method is applicable across a variety of architectures and vision datasets and, for the important and surprisingly hard task of detecting far-from-distribution out-of-distribution examples, it generally performs better than or equal to state-of-the-art OOD detection methods (including those that do assume access to OOD examples).