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.
NCRF transducers improve sequence labeling across tasks.
Improved neural transducer model outperforms attention model on longer sequences.
Improved speech recognition model with better performance.
A new method calculates optimal decisions from classifier outputs, improving predictions in drug discovery.
Dirichlet Process(DP) is a Bayesian non-parametric prior for infinite mixture modeling, where the number of mixture components grows with the number of data items. The Hierarchical Dirichlet Process (HDP), is an extension of DP for grouped data, often used for non-parametric topic modeling, where each group is a mixtur…
Framework for differentiating WFSTs for structured loss functions.
In this paper, we propose a non-parametric conditional factor regression (NCFR)model for domains with high-dimensional input and response. NCFR enhances linear regression in two ways: a) introducing low-dimensional latent factors leading to dimensionality reduction and b) integrating an Indian Buffet Process as a prior…
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (…
Develops STC for sequential data with missing labels.
Streamable model improves speech recognition performance.
User-specific KWS system learns new keywords on-device.
New methods improve integration of external LMs with AED models.
A new framework improves ASR alignment accuracy via optimal transport.
Modeling and learning turn-taking behaviors in multi-agent systems.
A fixed point theorem is proved for inverse transducers, leading to an automata-theoretic proof of the fixed point subgroup of an endomorphism of a finitely generated virtually free group being finitely generated. If the endomorphism is uniformly continuous for the hyperbolic metric, it is proved that the set of regula…
We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…
Conformal Prediction Regions match Imprecise Highest Density Regions under consonance.
This paper formalizes Uniswap v3 using PTA and FST for rigorous analysis.
Requirements elicitation can be very challenging in projects that require deep domain knowledge about the system at hand. As analysts have the full control over the elicitation process, their lack of knowledge about the system under study inhibits them from asking related questions and reduces the accuracy of requireme…
WEST compresses word embeddings and softmax layers for memory efficiency.
New ASR system handles multiple languages without needing language-specific encoding.
This study improves knowledge distillation for RNN-T models with noisy labels.
Phylogenetic tree reconstruction is traditionally based on multiple sequence alignments (MSAs) and heavily depends on the validity of this information bottleneck. With increasing sequence divergence, the quality of MSAs decays quickly. Alignment-free methods, on the other hand, are based on abstract string comparisons …
Requirements elicitation requires extensive knowledge and deep understanding of the problem domain where the final system will be situated. However, in many software development projects, analysts are required to elicit the requirements from an unfamiliar domain, which often causes communication barriers between analys…
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.