کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

An Iterative Post-processing Method for Speech Source Separation in Realistic Scenarios

نویسندگان :

Iman Shahriari¹ Hossein Zeinali²

1- Amirkabir University of Technology (Tehran Polytechnic) 2- Amirkabir University of Technology (Tehran Polytechnic)

کلمات کلیدی :

Speech Source Separation،Speaker Embedding،Deep Learning

چکیده :

The purpose of this paper is to design a speaker-independent Blind Source Separation (BSS) system which aims to reduce the word error rate (WER) metric on Persian speech data. The main idea behind this method is that it tries to improve the quality of the output of any baseline separation system with the help of an iterative model by removing the remained parts of the interferer speaker from each source. For this purpose, we use embedded representations of the input speech signals. In addition, our system benefits from a convergence metric that aims to purify the output signals. To evaluate the proposed method, we have collected a dataset that contains about one hour of real phone calls from landline phones. Although most of the energy of some consonant phonemes appears in high-frequency bins which are filtered in telephony speeches, our method can handle this condition by properly removing the interference. Experimental results based on different metrics have proved the effectiveness of the proposed method.

لیست مقالات

لیست مقالات بایگانی شده

A Low-cost Waveguide Switch Using Glide-symmetric Holey Electromagnetic Band Gap Technology

Mohsen Shafeghati - Elham Sharifi moghaddam - Behzad Ahmadi

Improving Artificial Neural Network Performance Using Hybrid Activation Function

Morteza Taheri - Sajad Haghzad Klidbary

Design and fabrication tip tapered fiber optic dopamine sensor based on LSPR

Roksana Esmaeilpour - Mohammad Ismail zibaii - Masoumeh Barkand - Marzieh Pajouhandeh - Soroush Rostami - Mehdi Banihashemi - Mohammad-Mahdi Babakhani-fard

Machine Learning-based Fundamental Stock Prediction Using Companies’ Financial Reports

Hossein Rezaei - Kamran Abdi - Mohsen Hooshmand

شناسایی گره‌های مهم سیستم قدرت با استفاده از ابزار شبکه‌های پیچیده و مرکزیت‌های مبتنی بر تشخیص جامعه

سپهر مردانی - علی کریمی - مهران معماری

Supercapacitor Active Balancing and Control Circuit for Harvesting Energy from Vehicle’s Tire

Mostafa Noohi - Ali Mirvakili

T-type L-2L De-Embedding Method for On-Wafer T-model Transmission Line Network

Milad Seyedi - Nasser Masoumi - Samad Sheikhaei

Simulation of planar organic-inorganic perovskite light-emitting diode

Morteza Yarahmadi - Elnaz Yazdani - Mohammad Kazem Moravvej-Farshi

A Communication-Aware Scheduler for Containers in a Kubernetes Environment Using Girvan-Newman Clustering

Marzie Norouzi Dehnashi - Mahmoud Momtazpour - Seyyed Ahmad Javadi

BLSTM-Convolutional Neural Networks for Respiratory Disease Diagnosis

Mohammad Hassan Khamechian - Mohammad Reza Akbarzadeh Tootoonchi

بیشتر