TY - JOUR
T1 - Hidden Markov model-based packet loss concealment for voice over IP
AU - Rødbro, Christoffer A.
AU - Murthi, Manohar N.
AU - Andersen, Søren Vang
AU - Jensen, Søren Holdt
N1 - Funding Information:
Manuscript received September 2, 2004; revised May 9, 2005. The work of M. N. Murthi was supported in part by the National Science Foundation under CAREER Award CCF-0347229. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Arun C. Surendran.
PY - 2006/9
Y1 - 2006/9
N2 - As voice over IP proliferates, packet loss concealment (PLC) at the receiver has emerged as an important factor in determining voice quality of service. Through the use of heuristic variations of signal and parameter repetition and overlap-add interpolation to handle packet loss, conventional PLC systems largely ignore the dynamics of the statistical evolution of the speech signal, possibly leading to perceptually annoying artifacts. To address this problem, we propose the use of hidden Markov models for PLC. With a hidden Markov model (HMM) tracking the evolution of speech signal parameters, we demonstrate how PLC is performed within a statistical signal processing framework. Moreover, we show how the HMM is used to index a specially designed PLC module for the particular signal context, leading to signal-contingent PLC. Simulation examples, objective tests, and subjective listening tests are provided showing the ability of an HMM-based PLC built with a sinusoidal analysis/synthesis model to provide better loss concealment than a conventional PLC based on the same sinusoidal model for all types of speech signals, including onsets and signal transitions.
AB - As voice over IP proliferates, packet loss concealment (PLC) at the receiver has emerged as an important factor in determining voice quality of service. Through the use of heuristic variations of signal and parameter repetition and overlap-add interpolation to handle packet loss, conventional PLC systems largely ignore the dynamics of the statistical evolution of the speech signal, possibly leading to perceptually annoying artifacts. To address this problem, we propose the use of hidden Markov models for PLC. With a hidden Markov model (HMM) tracking the evolution of speech signal parameters, we demonstrate how PLC is performed within a statistical signal processing framework. Moreover, we show how the HMM is used to index a specially designed PLC module for the particular signal context, leading to signal-contingent PLC. Simulation examples, objective tests, and subjective listening tests are provided showing the ability of an HMM-based PLC built with a sinusoidal analysis/synthesis model to provide better loss concealment than a conventional PLC based on the same sinusoidal model for all types of speech signals, including onsets and signal transitions.
KW - Hidden Markov models (HMMs)
KW - Internet telephony
KW - Packet loss
KW - Packet loss concealment
KW - Packet switching
KW - Speech coding
KW - Speech communication
KW - Voice over IP
UR - http://www.scopus.com/inward/record.url?scp=33744969796&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33744969796&partnerID=8YFLogxK
U2 - 10.1109/TSA.2005.858561
DO - 10.1109/TSA.2005.858561
M3 - Article
AN - SCOPUS:33744969796
VL - 14
SP - 1609
EP - 1623
JO - IEEE Transactions on Speech and Audio Processing
JF - IEEE Transactions on Speech and Audio Processing
SN - 1558-7916
IS - 5
ER -