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.
This paper improves ASR performance by aligning frames more accurately.
We present a solution to "Google Cloud and YouTube-8M Video Understanding Challenge" that ranked 5th place. The proposed model is an ensemble of three model families, two frame level and one video level. The training was performed on augmented dataset, with cross validation.
Voice activity detection (VAD), which classifies frames as speech or non-speech, is an important module in many speech applications including speaker verification. In this paper, we propose a novel method, called self-adaptive soft VAD, to incorporate a deep neural network (DNN)-based VAD into a deep speaker embedding …
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) …
SOM-VQ tokenizes discrete models with semantic structure and navigable topology.
We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach (as opposed to LDA) for intersession variability compensation in the i-…
We study large-scale kernel methods for acoustic modeling in speech recognition and compare their performance to deep neural networks (DNNs). We perform experiments on four speech recognition datasets, including the TIMIT and Broadcast News benchmark tasks, and compare these two types of models on frame-level performan…
Patient pain can be detected highly reliably from facial expressions using a set of facial muscle-based action units (AUs) defined by the Facial Action Coding System (FACS). A key characteristic of facial expression of pain is the simultaneous occurrence of pain-related AU combinations, whose automated detection would …
In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and quantify their contributions. The techniques include: 1) a nearest-neig…
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN…
Detecting temporal extents of human actions in videos is a challenging computer vision problem that requires detailed manual supervision including frame-level labels. This expensive annotation process limits deploying action detectors to a limited number of categories. We propose a novel method, called WSGN, that learn…
In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras. We propose a Siamese framework in which video frames of the person to re-identify and of the candidate one are processed by two ide…
In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming on-device speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery co…
We describe a graph-based semi-supervised learning framework in the context of deep neural networks that uses a graph-based entropic regularizer to favor smooth solutions over a graph induced by the data. The main contribution of this work is a computationally efficient, stochastic graph-regularization technique that u…
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedd…
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been widely used in video captioning. In existing literature, the attention weights are often built from the information of an individual modali…
This paper surveys scalable automated alignment methods for LLMs.
Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly employ supervised learning models that predict various time-frequency represent…
Inference-aware meta-alignment of LLMs reduces computational cost.
Conformal Alignment ensures trustworthy outputs from foundation models.
LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
The paper proposes a learning-theoretic perspective on representation alignment.
Fastest video anomaly detection via teacher-student distillation.
Survey of alignment techniques for large language models.
The paper addresses rigid alignment of noisy patches, providing a polynomial time algorithm and convergence conditions.
Study connects database alignment and planted matching using Gaussian features.
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in …
Bayesian framework proves thresholds for multi-graph alignment feasibility.
SMAI framework tests and integrates single-cell data alignability.
New method aligns brain data across individuals for better brain decoding.
Method aligns multilingual news for better stock return prediction.
This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obta…
Hölder-DPO aligns models robustly with noisy human feedback.
This paper improves cross-domain learning using random forests for manifold alignment.
Detecting correlated trees helps align sparse graphs.
We study alignment in linear neural networks and its relation to gradient descent.
Proposes ACCA for better alignment of multiple data perspectives.
Unified framework for aligning and composing diffusion models to satisfy multiple constraints.
Study improves understanding and performance of FA learning rules in neural networks.
DFA trains deep networks by aligning weights then memorizing data.
The study explains how neural networks align their kernels to target functions during training.
We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual informatio…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences between individual data-points. The proposed method requires only a few aligned exam…
LLM safety alignment explained as divergence estimation.
This study presents the results of a series of simulation experiments that evaluate and compare four different manifold alignment methods under the influence of noise. The data was created by simulating the dynamics of two slightly different double pendulums in three-dimensional space. The method of semi-supervised fea…
Align-RUDDER improves reinforcement learning with few demonstrations by redistributing rewards.
New model optimizes feature alignment, improving statistical and computational efficiency.