English
Related papers

Related papers: Accommodating Sample Size Effect on Similarity Mea…

200 papers

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions…

Sound · Computer Science 2022-07-04 Deja Kamil , Sanchez Ariadna , Roth Julian , Cotescu Marius

With its crosslinguistic and cross-speaker diversity, the Mozilla Common Voice Corpus (CV) has been a valuable resource for multilingual speech technology and holds tremendous potential for research in crosslinguistic phonetics and speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Miao Zhang , Aref Farhadipour , Annie Baker , Jiachen Ma , Bogdan Pricop , Eleanor Chodroff

We propose semantic smoothing, a smoothing method for language models that uses embeddings to share statistical observations across semantically similar contexts. The starting point is a decomposition of log-perplexity that motivates…

Information Theory · Computer Science 2026-05-11 Haricharan Balasundaram , Swathi Shree Narashiman , Pranay Mathur , Andrew Thangaraj

Recent advancements in large language models (LLMs) have shown their remarkable capacities in many NLP tasks. However, their substantial size often presents challenges for deployment. This necessitates efficient techniques for model…

Computation and Language · Computer Science 2026-05-20 Robin Baki Davidsson , Pierre Nugues

The objective of this work is effective speaker diarisation using multi-scale speaker embeddings. Typically, there is a trade-off between the ability to recognise short speaker segments and the discriminative power of the embedding,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Youngki Kwon , Hee-Soo Heo , Jee-weon Jung , You Jin Kim , Bong-Jin Lee , Joon Son Chung

We study the problem of closeness testing for continuous distributions and its implications for causal discovery. Specifically, we analyze the sample complexity of distinguishing whether two multidimensional continuous distributions are…

Machine Learning · Computer Science 2025-03-11 Fateme Jamshidi , Sina Akbari , Negar Kiyavash

We analyse the clustering of matter on large scales in an extension of the concordance model that allows for spatial curvature. We develop a consistent approach to curvature and wide-angle effects on the galaxy 2-point correlation function…

Cosmology and Nongalactic Astrophysics · Physics 2022-10-04 Julien Bel , Julien Larena , Roy Maartens , Christian Marinoni , Louis Perenon

In this paper, we explore the possibility of speech synthesis from low quality found data using only limited number of samples of target speaker. We try to extract only the speaker embedding from found data of target speaker unlike previous…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-15 Sunghee Jung , Hoirin Kim

This paper focuses on improving the accuracy of noise audio recordings. High-quality audio recording, extraction using the mel frequency cepstral coefficients (MFCC) method produces high accuracy. While the low-quality is because of noise,…

Sound · Computer Science 2022-01-03 Roy Rudolf Huizen , Florentina Tatrin Kurniati

Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e.g., reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL…

Computation and Language · Computer Science 2025-10-28 Afra Amini , Tim Vieira , Ryan Cotterell

Selecting an appropriate divergence measure is a critical aspect of machine learning, as it directly impacts model performance. Among the most widely used, we find the Kullback-Leibler (KL) divergence, originally introduced in kinetic…

Mathematical Physics · Physics 2025-07-16 Gennaro Auricchio , Giovanni Brigati , Paolo Giudici , Giuseppe Toscani

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-10 Wei Xia , John H. L. Hansen

Wide conditions are provided to guarantee asymptotic unbiasedness and L^2-consistency of the introduced estimates of the Kullback-Leibler divergence for probability measures in R^d having densities w.r.t. the Lebesgue measure. These…

Statistics Theory · Mathematics 2019-07-02 Alexander Bulinski , Denis Dimitrov

Adaptations of features commonly applied in the field of visual computing, co-occurrence matrix (COM) and run-length matrix (RLM), are proposed for the similarity computation of strings in general (words, phrases, codes and texts). The…

Machine Learning · Computer Science 2026-05-15 E. O. Rodrigues , D. Casanova , M. Teixeira , V. Pegorini , F. Favarim , E. Clua , A. Conci , Panos Liatsis

This paper shows that large nonparametric classes of conditional multivariate densities can be approximated in the Kullback--Leibler distance by different specifications of finite mixtures of normal regressions in which normal means and…

Statistics Theory · Mathematics 2010-10-05 Andriy Norets

Clustering is a central approach for unsupervised learning. After clustering is applied, the most fundamental analysis is to quantitatively compare clusterings. Such comparisons are crucial for the evaluation of clustering methods as well…

Machine Learning · Statistics 2017-10-03 Alexander J Gates , Yong-Yeol Ahn

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common speaker embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-21 Taous Iatariene , Alexandre Guérin , Romain Serizel

We propose a novel method to determine the dissimilarity between subjects for functional data clustering. Spline smoothing or interpolation is common to deal with data of such type. Instead of estimating the best-representing curve for each…

Methodology · Statistics 2021-03-23 ShengLi Tzeng , Christian Hennig , Yu-Fen Li , Chien-Ju Lin

In order to improve the performance for far-field speech recognition, this paper proposes to distill knowledge from the close-talking model to the far-field model using parallel data. The close-talking model is called the teacher model. The…

Computation and Language · Computer Science 2018-02-21 Jiangyan Yi , Jianhua Tao , Zhengqi Wen , Bin Liu

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Wenda Chen , Jonathan Huang , Tobias Bocklet