%Aigaion2 BibTeX export from Idiap Publications %Saturday 23 November 2024 05:15:45 AM @ARTICLE{Motlicek_EURASIP-2_2009, author = {Motlicek, Petr and Ganapathy, Sriram and Hermansky, Hynek and Garudadri, Harinath}, editor = {Raj, Bhiksha}, keywords = {Audio Coding, speech coding, speech quality evaluations}, projects = {Idiap}, month = {2}, title = {Wide-Band Audio Coding based on Frequency Domain Linear Prediction}, journal = {EURASIP Journal on Audio Speech and Music Processing}, volume = {2010}, number = {856280}, year = {2010}, note = {Special Issue: Scalable Audio-Content Analysis}, url = {http://www.hindawi.com/journals/asmp/2010/856280.html}, doi = {10.1155/2010/856280}, crossref = {Motlicek_Idiap-RR-32-2009}, abstract = {We revisit an original concept of speech coding in which the signal is separated into the carrier modulated by the signal envelope. A recently developed technique, called frequency-domain linear prediction (FDLP,',','), is applied for the efficient estimation of the envelope. The processing in the temporal domain allows for a straightforward emulation of the forward temporal masking. This, combined with an efficient nonuniform sub-band decomposition and application of noise shaping in spectral domain instead of temporal domain (a technique to suppress artifacts in tonal audio signals,',','), yields a codec that does not rely on the linear speech production model but rather uses well-accepted concept of frequency-selective auditory perception. As such, the codec is not only specific for coding speech but also well suited for coding other important acoustic signals such as music and mixed content. The quality of the proposed codec at 66{\^{a}}€‰kbps is evaluated using objective and subjective quality assessments. The evaluation indicates competitive performance with the MPEG codecs operating at similar bit rates.}, pdf = {https://publications.idiap.ch/attachments/papers/2010/Motlicek_EURASIP-2_2009.pdf} } crossreferenced publications: @TECHREPORT{Motlicek_Idiap-RR-32-2009, author = {Motlicek, Petr and Ganapathy, Sriram and Hermansky, Hynek}, projects = {Idiap}, month = {12}, title = {Wide-Band Audio Coding based on Frequency Domain Linear Prediction}, type = {Idiap-RR}, journal = {EURASIP Journal on Audio, Speech, and Music Processing}, volume = {Special Issue on}, number = {Idiap-RR-32-2009}, year = {2009}, institution = {Idiap}, address = {Rue Marconi 19, Martigny}, abstract = {In this paper, we re-visit an original concept of speech coding in which the signal is separated into the carrier modulated by the signal envelope. A recently developed technique, called frequency domain linear prediction (FDLP,',','), is applied for the efficient estimation of the envelope. The processing in the temporal domain allows for a straightforward emulation of the forward temporal masking. This, combined with an efficient non-uniform sub-band decomposition and application of noise shaping in spectral domain instead of temporal domain (a technique to suppress artifacts in tonal audio signals,',','), yields a codec that does not rely on the linear speech production model but rather uses well accepted concept of frequency-selective auditory perception. As such, the codec is not only specific for coding speech but also well suited for coding other important acoustic signals such as music and mixed content. The quality of the proposed codec at 66 kbps is evaluated using objective and subjective quality assessments. The evaluation indicates competitive performance with the MPEG codecs operating at similar bit-rates.}, pdf = {https://publications.idiap.ch/attachments/reports/2009/Motlicek_Idiap-RR-32-2009.pdf} }