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.

169,341 papers · 148 categories

Trend · papers per month

92185277369 · Jun 202019922001200920182026
48 results for end-to-end dialog system

This paper introduces a new method for dialog state tracking.

problem Accurately estimating dialog state from noisy observations.
method Bilinear algebraic decomposition model with collective matrix factorization.
result The proposed tracker performs well compared to state-of-the-art trackers.

Study finds neural dialog models struggle with conversational tasks.

problem Insufficient understanding of dialog by neural models.
method Analysis of internal representations and evaluation of model performance.
result Neural dialog models lack key conversational skills like answering questions and inferring contradiction.

BoSsNet learns language and knowledge separately, improving task-oriented dialog performance.

problem End-to-end neural networks struggle with KB changes in task-oriented dialogs.
method Encoder-decoder architecture with Bag-of-Sequences memory.
result BoSsNet outperforms state-of-the-art models with >10% improvement on bAbI OOV test sets.

This study compares hierarchical and non-hierarchical models for open-domain multi-turn dialog generation.

problem Which kind of models (hierarchical or non-hierarchical) is better for open-domain multi-turn dialog generation?
method Systematically compared nearly all representative hierarchical and non-hierarchical models over the same experimental settings.
result Nearly all hierarchical models are worse than non-hierarchical models in open-domain multi-turn dialog generation, except for HRAN.

Improves generative Visual Dialog by asking diverse questions.

problem Generative Visual Dialog models degrade after a few rounds of interaction.
method Introduce a simple auxiliary objective to incentivize Qbot to ask diverse questions.
result Better dialog diversity, consistency, fluency, and detail with improved image relevance.

End-to-end deep learning detects emotions in real-life emergency calls.

problem Recognizing emotions in real-life emergency call center recordings.
method Used an end-to-end deep learning architecture trained on IEMOCAP and CEMO datasets.
result Obtained 45.6% Unweighted Accuracy Recall on CEMO with 4 classes, 76.9% on 2 classes (Anger, Neutral).

HRL improves open-domain dialog models by optimizing long-term conversational goals.

problem Challenges in open-domain dialog generation, including repetitive outputs, difficulty tracking conversational goals, and inappropriate text.
method Proposes VHRL, a hierarchical reinforcement learning approach using policy gradients to tune utterance-level embeddings of a variational sequence model.
result Significant improvements in human evaluation and automatic metrics over state-of-the-art dialog models.

Neural Assistant integrates knowledge reasoning and dialogue generation in a single model.

problem Challenges in task-oriented dialog systems, including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction.
method Develops a single neural network model that jointly predicts text responses and actions from conversation history and external knowledge.
result The model learns to reason on external knowledge with weak supervision, improving factual accuracy and language generation performance.

Novel RL algorithms learn from human interaction data without exploration.

problem Efficiently learning from off-policy data in reinforcement learning.
method Developed off-policy batch RL algorithms using KL-control and dropout-based uncertainty.
result Successfully learned multiple reward functions from human interaction data.

ClovaCall introduces a new Korean call speech corpus for contact centers.

problem Lack of large-scale call-based speech corpora for Korean dialog scenarios.
method Development of a new large-scale Korean call-based speech corpus (ClovaCall) in a restaurant reservation domain.
result Validation of the dataset with ASR models shows its effectiveness.

Proposes a VAE with a discrete bottleneck for better text generation.

problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.

End-to-end autonomous driving perception learns latent features for better performance.

problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.

End-to-end speech recognition system trained on GPUs and CPUs.

problem Building state-of-the-art speech recognition systems.
method Utilizes CPUs and GPUs for training, data augmentation, and neural network updates. Uses vocal tract length perturbation and acoustic simulator for data augmentation. Employed Horovod allreduce for training.
result Achieved 7.92% WER on proprietary English Bixby open domain test set using a Bidirectional Full Attention (BFA) model.

End-to-end system improves speaker verification using attention mechanism.

problem Improving text-dependent speaker verification accuracy.
method Speaker discriminative CNNs extract features, attention mechanism combines them, end-to-end training optimizes system.
result The proposed system achieves better performance on Windows 10 speaker verification task.

Enhanced Tacotron for Japanese speech synthesis improves naturalness.

problem Challenges in end-to-end Japanese speech synthesis due to pitch accents.
method Extended Tacotron with self-attention to capture pitch accent dependencies.
result Proposed systems show improvements but still lag behind traditional pipeline methods.

End-to-end audio recognition system improves accuracy.

problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.

Differentiable Algorithm Networks (DAN) enable composable robot learning.

problem Training robots to learn from limited data and imperfect models.
method Composable architecture of neural network modules, each encoding a differentiable robot algorithm and model, trained end-to-end from data.
result DAN modules adapt to one another and compensate for imperfect models and algorithms, achieving best overall system performance.

End-to-end TTS framework uses hard alignment to improve accuracy.

problem End-to-end TTS systems struggle with accurate alignment between input text and output acoustic features.
method Proposes a constrained alignment scheme with hard monotonic alignments, marginalized during training.
result Improves alignment learning and prediction in end-to-end TTS systems.

End-to-end deep learning boosts IM/DD fiber communication over dispersive channels.

problem Improving data transmission over dispersive IM/DD channels with memory.
method Bidirectional recurrent neural network (BRNN) for end-to-end deep learning of the communication system.
result End-to-end SBRNN achieves significant bit-error-rate reduction compared to FFNNs.

End-to-end deep learning optimizes optical fiber communication systems.

problem Optimizing the performance of optical fiber communication systems.
method Implementing an end-to-end deep neural network for transmitter, channel, and receiver optimization.
result Achieved bit error rates below 6.7% hard-decision forward error correction threshold.

New algorithm trains communication systems without a differentiable channel model.

problem Training communication systems with unknown or non-differentiable channel models.
method Iterative training between receiver and transmitter using true and approximated gradients.
result Works as well as model-based training and achieves state-of-the-art performance.

Graphemes outperform phonemes in end-to-end models for English Voice-search and multi-dialect tasks.

problem Comparing phoneme-based and grapheme-based sub-word units in end-to-end models.
method Detailed experiments comparing phoneme-based and grapheme-based end-to-end models on large vocabulary English Voice-search and multi-dialect tasks.
result Graphemes outperform phonemes in end-to-end models for English Voice-search and multi-dialect tasks.

HabitatAgent offers a multi-agent system for transparent housing consultation.

problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.

Paper proposes a faster method for evaluating DNN hardware and software designs.

problem Reducing time for evaluating different DNN hardware and software designs.
method Using virtual hardware models to estimate DNN performance at the concept phase.
result Up to 92% accuracy in predicting DNN inference processing time.