A Framework for Music-Speech Segregation using Music Fingerprinting and Acoustic Echo Cancellation Principle

نویسنده

  • F. Hussain
چکیده

Background interference creates voice intelligibility issue for listener. This research work considers background music as interference for communication through smart phone in areas with loud background music. This paper proposes a novel framework for background music segregation from human speech using music fingerprinting and acoustic echo cancellation. Initially, background music is searched in the database by music fingerprinting. Identified background music is registered and segregated using acoustic echo cancellation. Proposed approach generates better quality music speech segregation than existing algorithms. The research work is novel and segregates background music completely in comparison to existing approaches where single instruments are segregated successfully.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improvement of In-Car Speech Recognition by Acoustic Echo Canceller with Maximum Likelihood

In this paper, as a key technology for improvement of speech recognition system in car environments, we propose an acoustic echo canceller for selecting an optimum cancellation result based on the echo estimation with maximum likelihood using transfer characteristics measured prospectively. The results of experiments conducted to speech superimposed on music show that the proposed canceller can...

متن کامل

Investigating the formal effect of rear wall structure on acoustic parameters of speech halls (Research Article)

Referring to the rear wall in a hall is the furthest element rather than the voice source, therefor the reflections of this structural member play important role in music and speech intelligibly, especially for one-third behind audiences. Hence the form of these structures can be very effective in the acoustical quality of speech halls and auditoria. In this study, four formic structures are ex...

متن کامل

A hybrid technique for speech segregation and classification using a sophisticated deep neural network

Recent research on speech segregation and music fingerprinting has led to improvements in speech segregation and music identification algorithms. Speech and music segregation generally involves the identification of music followed by speech segregation. However, music segregation becomes a challenging task in the presence of noise. This paper proposes a novel method of speech segregation for un...

متن کامل

Efficient Multichannel NLMS Implementation for Acoustic Echo Cancellation

An acoustic echo cancellation structure with a single loudspeaker and multiple microphones is, from a system identification perspective, generally modelled as a single-input multiple-output system. Such a system thus implies specific echo-pathmodels (adaptive filter) for every loudspeaker tomicrophone path. Due to the often large dimensionality of the filters, which is required tomodel rooms wi...

متن کامل

Design and Optimization of a Speech Recognition Front-End for Distant-Talking Control of a Music Playback Device

This paper addresses the challenging scenario for the distanttalking control of a music playback device, a common portable speaker with four small loudspeakers in close proximity to one microphone. The user controls the device through voice, where the speech-to-music ratio can be as low as −30 dB during music playback. We propose a speech enhancement front-end that relies on known robust method...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015