A robust speech/music discriminator for switched audio coding. Fuchs, G. In 2015 23rd European Signal Processing Conference (EUSIPCO), pages 569-573, Aug, 2015.
![A robust speech/music discriminator for switched audio coding [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex
Paper doi abstract bibtex Switching between speech coding and generic audio coding schemes was recently proven to be very efficient for coding a large range of audio materials at low bit-rates. However, it strongly relies on a robust classification of the input signal. The aim of the paper is to design a reliable speech and music discriminator (SMD) for such an application. Main attention was laid on getting a good tradeoff between accuracy, reactivity and stability of the decision while keeping the delay and complexity reasonably low. To this end, short-term and long-term features are dissociated before being conveyed to two different classifiers. The two classifier outputs are combined in a final decision using a hysteresis. Objective measures show that a more reliable switching decision is achievable. The SMD was successfully implemented in MPEG Unified Speech and Audio Coding (USAC). It allows the codec to show unprecedented audio quality.
@InProceedings{7362447,
author = {G. Fuchs},
booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
title = {A robust speech/music discriminator for switched audio coding},
year = {2015},
pages = {569-573},
abstract = {Switching between speech coding and generic audio coding schemes was recently proven to be very efficient for coding a large range of audio materials at low bit-rates. However, it strongly relies on a robust classification of the input signal. The aim of the paper is to design a reliable speech and music discriminator (SMD) for such an application. Main attention was laid on getting a good tradeoff between accuracy, reactivity and stability of the decision while keeping the delay and complexity reasonably low. To this end, short-term and long-term features are dissociated before being conveyed to two different classifiers. The two classifier outputs are combined in a final decision using a hysteresis. Objective measures show that a more reliable switching decision is achievable. The SMD was successfully implemented in MPEG Unified Speech and Audio Coding (USAC). It allows the codec to show unprecedented audio quality.},
keywords = {audio coding;music;speech coding;audio quality;MPEG USAC;MPEG unified speech-audio coding;switching decision;SMD;robust signal classification;generic audio coding scheme;speech coding;switched audio coding;robust speech-music discriminator;Speech;Speech coding;Switches;Audio coding;Delays;Feature extraction;Speech and Music Discrimination;Speech},
doi = {10.1109/EUSIPCO.2015.7362447},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096727.pdf},
}Downloads: 0
{"_id":"SB9RFcs7L3ESPCCrf","bibbaseid":"fuchs-arobustspeechmusicdiscriminatorforswitchedaudiocoding-2015","authorIDs":[],"author_short":["Fuchs, G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["G."],"propositions":[],"lastnames":["Fuchs"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"A robust speech/music discriminator for switched audio coding","year":"2015","pages":"569-573","abstract":"Switching between speech coding and generic audio coding schemes was recently proven to be very efficient for coding a large range of audio materials at low bit-rates. However, it strongly relies on a robust classification of the input signal. The aim of the paper is to design a reliable speech and music discriminator (SMD) for such an application. Main attention was laid on getting a good tradeoff between accuracy, reactivity and stability of the decision while keeping the delay and complexity reasonably low. To this end, short-term and long-term features are dissociated before being conveyed to two different classifiers. The two classifier outputs are combined in a final decision using a hysteresis. Objective measures show that a more reliable switching decision is achievable. The SMD was successfully implemented in MPEG Unified Speech and Audio Coding (USAC). It allows the codec to show unprecedented audio quality.","keywords":"audio coding;music;speech coding;audio quality;MPEG USAC;MPEG unified speech-audio coding;switching decision;SMD;robust signal classification;generic audio coding scheme;speech coding;switched audio coding;robust speech-music discriminator;Speech;Speech coding;Switches;Audio coding;Delays;Feature extraction;Speech and Music Discrimination;Speech","doi":"10.1109/EUSIPCO.2015.7362447","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096727.pdf","bibtex":"@InProceedings{7362447,\n author = {G. Fuchs},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {A robust speech/music discriminator for switched audio coding},\n year = {2015},\n pages = {569-573},\n abstract = {Switching between speech coding and generic audio coding schemes was recently proven to be very efficient for coding a large range of audio materials at low bit-rates. However, it strongly relies on a robust classification of the input signal. The aim of the paper is to design a reliable speech and music discriminator (SMD) for such an application. Main attention was laid on getting a good tradeoff between accuracy, reactivity and stability of the decision while keeping the delay and complexity reasonably low. To this end, short-term and long-term features are dissociated before being conveyed to two different classifiers. The two classifier outputs are combined in a final decision using a hysteresis. Objective measures show that a more reliable switching decision is achievable. The SMD was successfully implemented in MPEG Unified Speech and Audio Coding (USAC). It allows the codec to show unprecedented audio quality.},\n keywords = {audio coding;music;speech coding;audio quality;MPEG USAC;MPEG unified speech-audio coding;switching decision;SMD;robust signal classification;generic audio coding scheme;speech coding;switched audio coding;robust speech-music discriminator;Speech;Speech coding;Switches;Audio coding;Delays;Feature extraction;Speech and Music Discrimination;Speech},\n doi = {10.1109/EUSIPCO.2015.7362447},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096727.pdf},\n}\n\n","author_short":["Fuchs, G."],"key":"7362447","id":"7362447","bibbaseid":"fuchs-arobustspeechmusicdiscriminatorforswitchedaudiocoding-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570096727.pdf"},"keyword":["audio coding;music;speech coding;audio quality;MPEG USAC;MPEG unified speech-audio coding;switching decision;SMD;robust signal classification;generic audio coding scheme;speech coding;switched audio coding;robust speech-music discriminator;Speech;Speech coding;Switches;Audio coding;Delays;Feature extraction;Speech and Music Discrimination;Speech"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","creationDate":"2021-02-13T17:31:52.337Z","downloads":0,"keywords":["audio coding;music;speech coding;audio quality;mpeg usac;mpeg unified speech-audio coding;switching decision;smd;robust signal classification;generic audio coding scheme;speech coding;switched audio coding;robust speech-music discriminator;speech;speech coding;switches;audio coding;delays;feature extraction;speech and music discrimination;speech"],"search_terms":["robust","speech","music","discriminator","switched","audio","coding","fuchs"],"title":"A robust speech/music discriminator for switched audio coding","year":2015,"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}