paper-with-me

Papers

Intrinsic normalization and extrinsic denormalization of formant data of vowels

2016-09-16 · T. V. Ananthapadmanabha, A. G. Ramakrishnan

Using a known speaker-intrinsic normalization procedure, formant data are scaled by the reciprocal of the geometric mean of the first three formant frequencies. This reduces the influence of the talker but results in a distorted vowel space. The proposed speaker-extrinsic procedure re-scales the normalized values by the mean formant values of vowels. When tested on the formant data of vowels published by Peterson and Barney, the combined approach leads to well separated clusters by reducing the spread due to talkers. The proposed procedure performs better than two top-ranked normalization procedures based on the accuracy of vowel classification as the objective measure.

📄 PDF Abstract BibTeX arXiv:1609.05104

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationVowel Classification

Similar Papers 제목 키워드 기반

Initial Model Incorporation for Deep Learning FWI: Pretraining or Denormalization?

2025-06-05 · Ruihua Chen, Bangyu Wu, Meng Li, Kai Yang

Subsurface property neural network reparameterized full waveform inversion (FWI) has emerged as an effective unsupervised learning framework, which can invert stably with an inaccurate starting model. It updates the trai…

Deep Learning

Face Deblurring Based on Separable Normalization and Adaptive Denormalization

2021-12-18 · Xian Zhang, Hao Zhang, Jiancheng Lv, Xiaojie Li

Face deblurring aims to restore a clear face image from a blurred input image with more explicit structure and facial details. However, most conventional image and face deblurring methods focus on the whole generated ima…

DeblurringFace ParsingSSIM

Hyper-Representations for Pre-Training and Transfer Learning

2022-07-22 · Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Re…

Knowledge DistillationNeural Architecture SearchRepresentation LearningSelf-Supervised Learning+2

On Training Derivative-Constrained Neural Networks

2023-10-02 · KaiChieh Lo, Daniel Huang

We refer to the setting where the (partial) derivatives of a neural network's (NN's) predictions with respect to its inputs are used as additional training signal as a derivative-constrained (DC) NN. This situation is co…

Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights

2022-09-29 · Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Re…

Knowledge DistillationNeural Architecture SearchTransfer Learning