English
Related papers

Related papers: Continuous time limits of the Utterance Selection …

200 papers

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…

Computation and Language · Computer Science 2025-10-15 Bajian Xiang , Shuaijiang Zhao , Tingwei Guo , Wei Zou

Language models suffer from various degenerate behaviors. These differ between tasks: machine translation (MT) exhibits length bias, while tasks like story generation exhibit excessive repetition. Recent work has attributed the difference…

Computation and Language · Computer Science 2022-10-21 Darcey Riley , David Chiang

We present recent results on the existence of a continuous time limit for Ensemble Kalman Filter algorithms. In the setting of continuous signal and observation processes, we apply the original Ensemble Kalman Filter algorithm proposed by…

Probability · Mathematics 2020-12-08 Theresa Lange , Wilhelm Stannat

This paper mainly investigates the strong convergence and stability of the truncated Euler-Maruyama (EM) method for stochastic differential delay equations with variable delay whose coefficients can be growing super-linearly. By…

Numerical Analysis · Mathematics 2021-08-10 Shounian Deng , Chen Fei , Weiyin Fei , Xuerong Mao

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Sound · Computer Science 2026-01-28 Tianhua Li , Chenda Li , Wei Wang , Xin Zhou , Xihui Chen , Jianqing Gao , Yanmin Qian

Stochastic time-varying optimization is an integral part of learning in which the shape of the function changes over time in a non-deterministic manner. This paper considers multiple models of stochastic time variation and analyzes the…

Optimization and Control · Mathematics 2023-02-23 Ali Yekkehkhany , Han Feng , Donghao Ying , Javad Lavaei

In many systems we can describe emergent macroscopic behaviors, quantitatively, using models that are much simpler than the underlying microscopic interactions; we understand the success of this simplification through the renormalization…

Biological Physics · Physics 2019-01-01 Leenoy Meshulam , Jeffrey L. Gauthier , Carlos D. Brody , David W. Tank , William Bialek

Recent research has explored the constrained generation capabilities of Large Language Models (LLMs) when explicitly prompted by few task-specific requirements. In contrast, we introduce Large-Scale Constraint Generation (LSCG), a new…

Computation and Language · Computer Science 2025-09-30 Matteo Boffa , Jiaxuan You

We have studied the dynamical properties of finite $N$-unit FitzHugh-Nagumo (FN) ensembles subjected to additive and/or multiplicative noises, reformulating the augmented moment method (AMM) with the Fokker-Planck equation (FPE) method [H.…

Statistical Mechanics · Physics 2007-08-27 Hideo Hasegawa

A common model of stochastic auto-regulatory gene expression describes promoter switching via cooperative protein binding, effective protein production in the active state and dilution of proteins. Here we consider an extension of this…

Subcellular Processes · Quantitative Biology 2020-04-07 James Holehouse , Abhishek Gupta , Ramon Grima

We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{\hat{\rho}_t^m}$ to its infinite-width counterpart $f_{\rho_t^{MF}}$, which…

Machine Learning · Statistics 2026-05-22 Margalit Glasgow , Joan Bruna

A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursive learning together for monaural speech enhancement. Apart…

Sound · Computer Science 2020-04-02 Andong Li , Chengshi Zheng , Cunhang Fan , Renhua Peng , Xiaodong Li

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Claudio Zito , Fabio Tesser , Mauro Nicolao , Piero Cosi

Selectively processing noisy utterances while effectively disregarding speech-specific elements poses no considerable challenge for humans, as they exhibit remarkable cognitive abilities to separate semantically significant content from…

Computation and Language · Computer Science 2024-10-08 Alina Wróblewska

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…

Computation and Language · Computer Science 2020-11-04 Mahdi Namazifar , Gokhan Tur , Dilek Hakkani Tür

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Computation and Language · Computer Science 2022-10-20 Chenghao Yang , Xuezhe Ma

We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…

Machine Learning · Statistics 2021-08-17 Dino Oglic , Zoran Cvetkovic , Peter Sollich

The current trend of scaling language models involves increasing both parameter count and training dataset size. Extrapolating this trend suggests that training dataset size may soon be limited by the amount of text data available on the…

We introduce a new method, allowing to describe slowly time-dependent Langevin equations through the behaviour of individual paths. This approach yields considerably more information than the computation of the probability density. The main…

Statistical Mechanics · Physics 2007-05-23 Nils Berglund , Barbara Gentz