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.

168,657 papers · 148 categories

Trend · papers per month

3570104139 · May 201919922001200920172026
48 results for accent embedding

GE2E-AC improves accent classification by focusing on accent embeddings.

problem Training models to predict accent type can lead to learning irrelevant features.
method GE2E-AC trains models to extract accent embeddings, making them closer for the same accent class.
result GE2E-AC outperforms baseline models trained with conventional loss.

This paper describes the data collection effort that is part of the project Sprekend Nederland (The Netherlands Talking), and discusses its potential use in Automatic Accent Location. We define Automatic Accent Location as the task to describe the accent of a speaker in terms of the location of the speaker and its hist…

2016-02-08abs ↗pdf ↗

State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems. However, a speech accent remains a challenge for both approaches. Phonologists ma…

2018-07-09abs ↗pdf ↗

The aim of this article is to present the category of bounded Frechet manifolds in respect to which we will review the geometry of Frechet manifolds with a stronger accent on its metric aspect. An inverse function theorem in the sense of Nash and Moser in this category is proved, and some applications to Riemannian geo…

2006-12-14abs ↗pdf ↗

Unified analysis of efficient local training methods for distributed variational inequalities.

problem Efficient distributed/federated learning for variational inequality problems.
method Unified convergence analysis of communication-efficient local training methods.
result First local gradient descent-accent algorithms with improved communication complexity.

Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly neglected, however, is discrimination of languages for multilingual speakers, d…

2020-01-29abs ↗pdf ↗

CL methods improve monolingual ASR models across new tasks without forgetting past data.

problem Catastrophic Forgetting in monolingual ASR models when adapting to new domains or accents.
method Implement and compare various Continual Learning methods for monolingual ASR.
result Best CL method reduces performance gap by over 40% with minimal past data.

This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully…

2018-11-05abs ↗pdf ↗

Proposes QQE for transforming and embedding data distributions.

problem Transforming and embedding data distributions for better representation or visualization.
method Quantile-Quantile Embedding (QQE) using quantile-quantile plot concept.
result QQE allows for better discrimination of classes in some cases.

Curvature regularization prevents distortion in graph embeddings.

problem Graph topology patterns distort in Euclidean space, making detection difficult.
method Proposes curvature regularization to enforce flatness in embedding manifolds.
result Significant improvements in five embedding methods on open graph datasets.

Word embeddings are a powerful approach for unsupervised analysis of language. Recently, Rudolph et al. (2016) developed exponential family embeddings, which cast word embeddings in a probabilistic framework. Here, we develop dynamic embeddings, building on exponential family embeddings to capture how the meanings of w…

2017-03-23abs ↗pdf ↗

Unified framework for word embedding models using noise examples.

problem Improving word embedding models with negative sampling.
method Formulated a Word-Context Classification (WCC) framework that generalizes SkipGram word embedding models.
result The best noise distribution is the data distribution, improving both performance and training speed.

The study characterizes and verifies equivariant embeddings of symmetric Kählerian manifolds.

problem Characterizing and verifying equivariant embeddings of symmetric Kählerian manifolds.
method Investigation motivated by Cartan and Wallach's theorem on symmetric spaces, focusing on CPn\mathbb{CP}^n and parallel plurimean curvature.
result If an equivariant embedding has parallel plurimean curvature, it is the extrinsically symmetric one.

The paper defines invariants for almost graph embeddings and explores their properties.

problem Understanding the properties and limitations of almost graph embeddings in the plane.
method Introducing and analyzing integer invariants (winding number, Wu numbers) for almost embeddings.
result Some values of invariants are realizable for almost embeddings but not for embeddings.

Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evol…

2018-12-06abs ↗pdf ↗

For leveled spatial graphs, we find a surface embedding that allows cellular embedding.

problem Finding a surface embedding for general spatial graphs is not always possible.
method Define leveled property, decompose graph into subgraphs, and construct surface.
result For leveled spatial graphs with a small number of levels, a surface can always be found.

Long spacelike embeddings can be approximated by isometric ones.

problem Approximating long embeddings to isometric embeddings in Lorentzian spaces.
method Proving approximation by constructing C1C^1 isometric embeddings.
result Long spacelike embeddings can be C0C^0-approximated by C1C^1 isometric embeddings.

A {\it wrinkled embedding} f:VnWmf:V^n\to W^m is a topological embedding which is a smooth embedding everywhere on VV except a set of (n1)(n-1)-dimensional spheres, where ff has cuspidal corners. In this paper we prove that any rotation of the tangent plane field TVTWTV\subset TW of a {\it smoothly embedded} submanifold $V\s…

2011-08-05abs ↗pdf ↗

Obtaining continuous representations of structural data such as directed acyclic graphs (DAGs) has gained attention in machine learning and artificial intelligence. However, embedding complex DAGs in which both ancestors and descendants of nodes are exponentially increasing is difficult. Tackling in this problem, we de…

2019-02-12abs ↗pdf ↗

Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data. However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it i…

2019-06-03abs ↗pdf ↗

Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The a…

2019-04-05abs ↗pdf ↗

Paper uses JIVE to decompose word embeddings, improving sentiment analysis performance.

problem Improving sentiment analysis performance on word embeddings.
method Joint and individual variance explained (JIVE) method for decomposition.
result Mapping word embeddings into joint components improves sentiment analysis performance.