Proceedings Article10.1109/ICIEM48762.2020.9160287
Speech Enhancement Using Semi-Supervised Learning
U Purushotham.,K S Chethan,S Manasa.,U Meghana. +3 more
- 01 Jun 2020
2
TL;DR: This paper considers semi-supervised machine learning algorithm to improve the quality of speech signal corrupted by environmental disturbance to show a considerable improvement in SNR by 5% to 8% as compared to that of conventional methods.
read more
Abstract: Speech enhancement using machine learning algorithm is one of the research problems in signal processing. The goal of the research is to enhance the speech signals, their by improving quality and intelligibility voice signals that are corrupted by real world environmental noise. In this paper we consider semi-supervised machine learning algorithm to improve the quality of speech signal corrupted by environmental disturbance. Most of the environmental disturbances are non-stationary i.e. the effect of noise is not uniform for all spectral components. In the proposed algorithm the system training is done using a set of speech and noise data base. Parameters are derived by calculating system performance. These parameters are used to enhance the speech signal. The results that are obtained show a considerable improvement in SNR by 5% to 8% as compared to that of conventional methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Towards Using Universal Big Data in Artificial Intelligence Research and Development to Gain Meaningful Insights and Automation Systems
Zainal A. Hasibuan
- 17 Oct 2020
TL;DR: The utilization of AI technology that penetrates end-to-end various aspects of human activities, such as in education, health, business, social life and so forth, leads to an AI automation system, with the power to generate meaningful insights suited to solve current problems, predicting trending issues, and understanding phenomena.
10
Semi-Supervised Speech Enhancement Based On Speech Purity
Zihao Cui,Shilei Zhang,Yanan Chen,Yingying Gao,Chao Deng,Jun-Huan Feng +5 more
- 04 Jun 2023
TL;DR: In this article , a semi-supervised speech enhancement framework is proposed to enhance typical speech datasets, which includes an estimator to measure the speech purity, and the training loss is designed as a combination of the supervised loss and unsupervised loss.
1
References
Electron Spectroscopy Studies on Magneto-Optical Media and Plastic Substrate Interface
TL;DR: In this paper, the depth profiles of amorphous TbFeCo films sputtered onto polycarbonate substrate were studied by X-ray photoelectron spectroscopy.
3.5K
Speech enhancement using excitation source information
B. Yegnanarayana,S. R. Mahadeva Prasanna,K. Sreenivasa Rao +2 more
- 13 May 2002
TL;DR: The characteristics of voiced speech can be used to derive a coherently added signal from the linear prediction (LP) residuals of the degraded speech data from different microphones to enhance speech degraded by noise and reverberation.
87
Spectro-Temporal Filtering for Multichannel Speech Enhancement in Short-Time Fourier Transform Domain
TL;DR: A number of experimental results show that the proposed spectro-temporal filtering method improves the performance of multichannel speech enhancement.
27
Reliable Semi-supervised Learning
Junming Shao,Chen Huang,Qinli Yang,Guangchun Luo +3 more
- 01 Dec 2016
TL;DR: A Reliable Semi-Supervised Learning framework, called ReSSL, is proposed, which model the reliability of cluster assumption, quantify the distinct importance of clusters, and integrate the cluster-level information and labeled data for prediction with a lazy learning framework.
20
Algorithm selection and software time/Space optimization for a DSP micro-based speech processor for a multi-electrode cochlear implant
L. Morris,P. Barszczewski,J. Bosloy +2 more
- 01 Apr 1987
TL;DR: This programmable system provides a flexible foundation for exploring the utility of other fundamental speech features in addition to pitch and formants for excitation of a cochlear prosthesis.
8