相关论文: Statistical Speech Model Description with VMF Mixt…

We introduce and test methods for the calibration of the diffusion term in Stochastic Partial Differential Equations (SPDEs) describing fluids. We take two approaches, one uses ideas from the singular value decomposition and the Biot-Savart…

Mathematical modelling, particularly through approaches such as structured sparse support vector machines (SS-SVM), plays a crucial role in processing data with complex feature structures, yet efficient algorithms for distributed…

Optical networks are vulnerable to physical layer attacks; wiretappers can improperly receive messages intended for legitimate recipients. Our work considers an aspect of this security problem within the domain of multimode fiber (MMF)…

The performance of speaker recognition system is highly dependent on the amount of speech used in enrollment and test. This work presents a detailed experimental review and analysis of the GMM-SVM based speaker recognition system in…

In reverberant conditions with multiple concurrent speakers, each microphone acquires a mixture signal of multiple speakers at a different location. In over-determined conditions where the microphones out-number speakers, we can narrow down…

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the short-time Fourier…

Visual Question Answering (VQA) emerges as one of the most fascinating topics in computer vision recently. Many state of the art methods naively use holistic visual features with language features into a Long Short-Term Memory (LSTM)…

We propose an information theoretic framework for quantitative assessment of acoustic modeling for hidden Markov model (HMM) based automatic speech recognition (ASR). Acoustic modeling yields the probabilities of HMM sub-word states for a…

Large Language Models (LLMs) have achieved remarkable breakthroughs. However, the huge number of parameters in LLMs require significant amount of memory storage in inference, which prevents their practical deployment in many applications.…

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep filtering (DF) recently demonstrated its capabilities for low-latency scenarios like hearing…

Beam search, which is the dominant ASR decoding algorithm for end-to-end models, generates tree-structured hypotheses. However, recent studies have shown that decoding with hypothesis merging can achieve a more efficient search with…

One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

In this work, we propose the marginal structured SVM (MSSVM) for structured prediction with hidden variables. MSSVM properly accounts for the uncertainty of hidden variables, and can significantly outperform the previously proposed latent…

Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of…

Time-series forecasting often faces challenges due to data volatility, which can lead to inaccurate predictions. Variational Mode Decomposition (VMD) has emerged as a promising technique to mitigate volatility by decomposing data into…

State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…

The primary objective of Stochastic Frontier (SF) Analysis is the deconvolution of the estimated composed error terms into noise and inefficiency. Assuming a parametric production function (e.g. Cobb-Douglas, Translog, etc.), might lead to…

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…

The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy. However, current PFL techniques…