%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:16:12 PM

@INPROCEEDINGS{motlicek:TSD:2007,
         author = {Motlicek, Petr and Hermansky, Hynek and Ganapathy, Sriram and Garudadri, Harinath},
       projects = {Idiap},
          title = {Non-Uniform Speech/Audio Coding Exploiting Predictability of Temporal Evolution of Spectral Envelopes},
      booktitle = {Tenth International Conference on TEXT, SPEECH and DIALOGUE ({TSD})},
           year = {2007},
           note = {IDIAP-RR 06-30},
       crossref = {motlicek:rr06-30},
       abstract = {Unlike classical state-of-the-art coders that are based on short-term spectra, our approach uses relatively long temporal segments of audio signal in critical-band-sized sub-bands. We apply auto-regressive model to approximate Hilbert envelopes in frequency sub-bands. Residual signals (Hilbert carriers) are demodulated and thresholding functions are applied in spectral domain. The Hilbert envelopes and carriers are quantized and transmitted to the decoder. Our experiments focused on designing speech/audio coder to provide broadcast radio-like quality audio around 15-25kbps. Obtained objective quality measures, carried out on standard speech recordings, were compared to the state-of-the-art 3GPP-AMR speech coding system.},
            pdf = {https://publications.idiap.ch/attachments/papers/2007/motlicek-TSD-2007.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2007/motlicek-TSD-2007.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{motlicek:rr06-30,
         author = {Motlicek, Petr and Hermansky, Hynek and Garudadri, Harinath and Srinivasamurthy, Naveen},
       projects = {Idiap},
          title = {Audio Coding Based on Long Temporal Contexts},
           type = {Idiap-RR},
         number = {Idiap-RR-30-2006},
           year = {2006},
    institution = {IDIAP},
       abstract = {We describe novel audio coding technique designed to be utilized at medium bit-rates. Unlike classical state-of-the-art audio coders that are based on short-term spectra, our approach uses relatively long temporal segments of audio signal in critical-band-sized sub-bands. We apply auto-regressive model to approximate Hilbert envelopes in frequency sub-bands. Residual signals (Hilbert carriers) are demodulated and thresholding functions are applied in spectral domain. The Hilbert envelopes and carriers are quantized and transmitted to the decoder. Our experiments focused on designing audio coder to provide broadcast radio-like quality audio around $10-20$kbps. Objective quality measures indicate comparable performance with the 3GPP-AMR speech codec standard for both speech and non-speech signals.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/motlicek-idiap-rr-06-30.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/motlicek-idiap-rr-06-30.ps.gz},
ipdmembership={speech},
}