Related papers: Continuous time limits of the Utterance Selection …

We consider linearizations of stochastic differential equations with additive noise using the Karhunen-Lo\`eve expansion. We obtain our linearizations by truncating the expansion and writing the solution as a series of matrix-vector…

This paper introduces a continuous-time stochastic dynamical framework for understanding how large language models (LLMs) may self-amplify latent biases or toxicity through their own chain-of-thought reasoning. The model posits an…

We present a full stochastic description of the pair approximation scheme to study binary-state dynamics on heterogeneous networks. Within this general approach, we obtain a set of equations for the dynamical correlations, fluctuations and…

Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended…

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Short-utterance speaker verification remains challenging due to limited speaker-discriminative cues in short speech segments. While existing methods focus on enhancing speaker encoders, the embedding learning strategy still forces a single…

We develop a high-dimensional scaling limit for Stochastic Gradient Descent with Polyak Momentum (SGD-M) and adaptive step-sizes. This provides a framework to rigourously compare online SGD with some of its popular variants. We show that…

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

We study the large-scale behaviour of a family of stochastic reaction-diffusion equations driven by long-range correlated noise in a weakly nonlinear regime. Depending on the decay of correlations of the noise and the strength of the…

In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

Stochastic gradient descent (SGD) has been widely used in machine learning due to its computational efficiency and favorable generalization properties. Recently, it has been empirically demonstrated that the gradient noise in several deep…

Motivated by engineering applications such as resource allocation in networks and inventory systems, we consider average-reward Reinforcement Learning with unbounded state space and reward function. Recent works studied this problem in the…

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features…

An Euler-type framework with equidistant step sizes is proposed for a class of time-changed stochastic differential equations.We establish the strong convergence rate of the standard Euler--Maruyama method under the global Lipschitz…

We investigate the performance of large language models on repetitive deterministic prediction tasks and study how the sequence accuracy rate scales with output length. Each such task involves repeating the same operation n times. Examples…

Many studies have shown that human languages tend to optimize for lower complexity and increased communication efficiency. Syntactic dependency distance, which measures the linear distance between dependent words, is often considered a key…

A key barrier to making phonetic studies scalable and replicable is the need to rely on subjective, manual annotation. To help meet this challenge, a machine learning algorithm was developed for automatic measurement of a widely used…

Speech language models (LMs) are promising for high-quality speech synthesis through in-context learning. A typical speech LM takes discrete semantic units as content and a short utterance as prompt, and synthesizes speech which preserves…

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…