Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

0.3%0.6%0.9%1.3% · Jun 202319922001200920172026
48 results for client utterances

Modeling long-range context for multi-function utterances in dialogues.

problem Complex dependencies across dialogue turns in long utterances.
method Adapted Convolutional Recurrent Neural Network (CRNN) to model interactions between utterances.
result Significantly outperforms existing work on CDA recognition on a tech forum dataset.

Meta-learning framework improves short utterance speaker recognition.

problem Poor performance of existing models with short utterances.
method Prototypical Networks with support and query sets, enforcing classification against entire training set.
result Significant performance gains on VoxCeleb datasets.

Improves speaker verification for variable-duration utterances using a feature pyramid module.

problem Improving robustness for variable-duration utterances in speaker verification.
method Integrates a feature pyramid module into multi-scale aggregation to enhance speaker-discriminative information from multiple layers.
result Improves performance for both short and long utterances compared to state-of-the-art approaches.

Graphical lasso models ASR utterance dependencies for consistent WER estimation.

problem Modeling dependent structure among ASR utterances for accurate significance analysis.
method Graphical lasso for dependency modeling, followed by blockwise bootstrap resampling.
result Statistically consistent variance estimator of WER under mild conditions.

Self multi-head attention improves speaker recognition for long utterances.

problem Speaker recognition for long speech segments using Deep Learning.
method Convolutional Neural Network (CNN) for short-term features, self multi-head attention for long-term embeddings.
result Self multi-head attention outperforms other pooling methods by 18% relative EER on VoxCeleb1 dataset.

Improved far-field speaker verification for short utterances in noisy conditions.

problem Challenges in speaker verification on short utterances in uncontrolled noisy environments.
method Used deep neural network architectures (TDNN and ResNet) and experimented with various embedding extractors and training procedures.
result ResNet architectures outperform x-vector approach in speaker verification quality for both long and short utterances.

DGP learns speech recognition by modeling complex relationships between utterances.

problem Modeling complex relationships in speech recognition without relational data.
method Bayesian nonparametric deep learning method (DGP) that generates infinite probabilistic graphs.
result DGP successfully infers relationships among utterances without relational data during training.

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …

2017-01-03abs ↗pdf ↗

Client adaptation improves federated learning performance with non-IID data.

problem Improving model performance in federated learning with non-identically and non-independently distributed data.
method Simulates heterogeneous clients to learn client-specific conditioning using a conditional gated activation unit.
result Client adaptation enhances model performance across balanced and imbalanced data sets from audio and image domains.

FedSTaS stratifies and samples clients for efficient FL.

problem Inefficient client sampling in federated learning.
method Stratifies clients based on compressed gradients, uses Neyman allocation for sampling, and samples local data uniformly.
result FedSTaS achieves higher accuracy than FedSTS in fixed training rounds.

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We sh…

2015-06-24abs ↗pdf ↗

This paper analyzes and improves convergence in federated learning with biased client selection.

problem Analyzing convergence in federated learning with biased client selection.
method First convergence analysis of federated optimization for biased client selection strategies, proposing Power-of-Choice framework.
result Power-of-Choice strategies converge up to 3 times faster and give 10% higher test accuracy than random selection.

This paper optimizes brokerage contracts for multiple clients trading a single asset.

problem Optimizing brokerage contracts for multiple clients trading a single asset.
method Endogenously determines clients' reservation values and strategically chooses clients. Characterizes optimal portfolios computationally.
result Characterizes optimal portfolios of clients and their profits, showing dependence on price impact coefficients.

Active Federated Learning selects clients to maximize efficiency.

problem Minimizing bandwidth usage and maximizing model accuracy in federated learning.
method Clients are selected with a probability conditioned on the current model and client data to maximize efficiency.
result Reduces the number of required training iterations by 20-70% while maintaining the same model accuracy.

Personalized federated learning for diverse client objectives.

problem Training a single global model across diverse local datasets is not optimal.
method Efficiently calculates optimal weighted model combinations for each client based on their specific objectives.
result Our method outperforms existing alternatives and enables new personalized features.

This work detects anomalous clients in federated learning to prevent their adverse impacts.

problem Detecting and preventing anomalous client behaviors in federated learning systems.
method Generates low-dimensional surrogates of model weight vectors and uses them for anomaly detection.
result The proposed detection-based approach significantly outperforms conventional defense-based methods.

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to s…

2017-12-20abs ↗pdf ↗

FedAMD framework improves federated learning with partial client participation.

problem Data heterogeneity and inactive client updates in partial client participation.
method Anchor sampling divides clients into anchor and miner groups, using large and small batches respectively.
result FedAMD achieves faster convergence and improved model performance compared to state-of-the-art methods.

Federated framework learns causal states to predict counterfactuals without centralizing data.

problem Decentralized counterfactual reasoning in coupled industrial systems with private data.
method Federated causal representation learning in state-space systems.
result Proves convergence to centralized oracle and provides privacy guarantees.

The paper extracts structured data from physician-patient conversations, reducing clerical burden.

problem Mining insights from physician-patient conversations for electronic health record documentation.
method Created a dataset of transcripts and summaries, extracted noteworthy utterances, and improved model performance.
result Extracting noteworthy utterances significantly boosts model performance for recognizing diagnoses and RoS abnormalities.

Unified Bayesian framework for clustered federated learning improves model performance.

problem Handling non-IID client data in federated learning.
method A unified Bayesian framework for clustered federated learning that associates clients to clusters and proposes practical algorithms for data associations.
result The proposed framework increases model performance by circumventing the need for unique client-cluster associations.

FLowDUP trains personalized models with unlabeled clients in low dimensions.

problem Training personalized models on clients with only unlabeled data.
method FLowDUP uses a forward pass with unlabeled data and a transductive PAC-Bayesian bound to generate personalized models in a low-dimensional subspace.
result FLowDUP enables efficient communication and computation with personalized models generated from unlabeled data.

Federated learning algorithm improves with intermittent client availability.

problem Performance degradation in Federated Averaging due to client availability changes.
method Federated Latest Averaging (FedLaAvg) uses latest gradients from all clients, even when unavailable.
result FedLaAvg achieves sublinear speedup compared to classical Federated Averaging.

DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.

problem Efficiently train models with privacy and communication efficiency in federated learning.
method Decentralized Federated Averaging with Momentum (DFedAvgM) on clients connected by an undirected graph, using stochastic gradient descent with momentum and quantization.
result DFedAvgM converges under trivial assumptions and can be improved with the PŁ property, numerically verified.

Group personalization improves FL performance in heterogeneous client data.

problem Mitigating client drift in federated learning with heterogeneous data.
method Fine-tuning a global FL model over homogeneous groups of clients, then personalizing each group's model.
result The proposed method achieves superior personalization performance compared to other FL approaches.

FedACS uses attention to select clients with similar data for federated learning.

problem Non-IID data and data scarcity in federated learning.
method FedACS integrates an attention mechanism to prioritize clients with similar data distributions.
result FedACS improves federated learning performance by addressing non-IID data and data scarcity.

Optimal client sampling reduces communication in federated learning.

problem Efficiently aggregate model updates from distributed clients in federated learning.
method Model weights as an Ornstein-Uhlenbeck process to estimate uncommunicated updates; optimal client sampling strategy.
result Significant reduction in communication with competitive or superior performance.

Developers of text-to-speech synthesizers (TTS) often make use of human raters to assess the quality of synthesized speech. We demonstrate that we can model human raters' mean opinion scores (MOS) of synthesized speech using a deep recurrent neural network whose inputs consist solely of a raw waveform. Our best models …

2016-11-28abs ↗pdf ↗

A new framework for federated continual learning reduces interference and improves performance.

problem Learning from a sequence of tasks with limited data from each client.
method Federated Weighted Inter-client Transfer (FedWeIT) framework.
result FedWeIT significantly outperforms existing methods with reduced communication cost.

New method for semi-supervised learning in federated learning with and without labels at clients.

problem Training federated learning models with partially or completely unlabeled data.
method Federated Matching (FedMatch) with inter-client consistency loss and disjoint learning.
result FedMatch outperforms local semi-supervised learning and naive federated learning combinations.

A novel incentive mechanism improves fairness and participation in federated learning.

problem Low-quality clients and lack of fairness in federated learning.
method Client selection process and money transfer mechanism to ensure fairness and participation.
result The proposed incentive mechanism improves the duration and fairness of federated learning.

Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.

problem Optimizing personalized objectives in a distributed system with limited global information.
method Kernel-based bandit framework with surrogate Gaussian process models, sparse approximations.
result Order-optimal regret performance (up to polylogarithmic factors) and reduced communication overhead.