Overview of compression and packet loss effects in speech biometrics
Abstract
An overview is presented of compression and packet loss effects in speech biometrics. These new problems appear particularly in recent applications of biometrics over mobile or Internet networks. The influence of speech compression on speaker recognition performance in mobile networks is investigated. In a first experiment, it is found that the use of GSM coding degrades the performance. In a second experiment, the features for the speaker recognition system are calculated directly from the information available in the encoded bit stream. It is found that a low LPC order in GSM coding is responsible for most performance degradations. A speaker recognition system was obtained which is equivalent in performance to the original one which decodes and reanalyses speech before performing recognition. The joint packet loss and compression effects over IP networks are also studied. It is experimentally demonstrated that the adverse effects of packet loss alone are negligible, while the encoding of speech, particularly at a low bit rate, coupled with packet loss, can reduce the verification accuracy considerably.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Over mobile or internet networks, the combined effects of audio codec compression and channel transmission degradation reduce the speech quality.
“Additionally, over mobile or internet networks, the combined effects of audio codec compression and channel transmission degradation reduce the speech quality [28].”
From Benchmarking Audio Deepfake Detection Robustness in Real-World Communication Scenarios (2025) · cites this paper as [28]
Prior studies indicate that channel-induced data loss degrades the performance of audio-based feature systems.
“Prior studies indicate that channel-induced data loss degrades the performance of audio-based feature systems [28]”
From Benchmarking Audio Deepfake Detection Robustness in Real-World Communication Scenarios (2025) · cites this paper as [28]
Cites
Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
Gauvain, J.-L., & Lee, C. (1994) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.279278 · Cited by 2,095 · see citing works
Speaker identification and verification using Gaussian mixture speaker models
Reynolds, D. A. (1995) · Speech Communication · doi:10.1016/0167-6393(95)00009-d · Cited by 1,216 · see citing works
Score Normalization for Text-Independent Speaker Verification Systems
Auckenthaler, R., Carey, M. J., & Lloyd-Thomas, H. (2000) · Digital Signal Processing · doi:10.1006/dspr.1999.0360 · Cited by 698 · see citing works
Adaptive FEC-based error control for Internet telephony
Bolot, J.-C., Fosse-Parisis, S., & Towsley, D. (1999) · doi:10.1109/infcom.1999.752166 · Cited by 354 · see citing works
Second-order statistical measures for text-independent speaker identification
Bimbot, F., Magrin‐Chagnolleau, I., & Mathan, L. (1995) · Speech Communication · doi:10.1016/0167-6393(95)00013-e · Cited by 128 · see citing works
Normalizations and selection of speech segments for speaker recognition scoring
Li, K.-P., & Porter, J. E. (2003) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1988.196655 · Cited by 109 · see citing works
Recognizing voice over IP: a robust front-end for speech recognition on the world wide web
Peláez-Moreno, C., Gallardo-Antolín, A., & Díaz-de-María, F. (2001) · IEEE Transactions on Multimedia · doi:10.1109/6046.923820 · Cited by 64 · see citing works
Black, U. (1999) · Medical Entomology and Zoology · Cited by 55 · see citing works
Speech recognition from GSM codec parameters
Huerta, J. M., & Stern, R. M. (1998) · International Conference on Spoken Language Processing (ICSLP) · doi:10.21437/icslp.1998-329 · Cited by 48 · see citing works
Speaker and Language Recognition Using Speech Codec Parameters
Quatieri, T. F., Singer, E., Dunn, R. B., et al. (1999) · doi:10.21236/ada526525 · Cited by 46 · see citing works
Ben, M., Blouet, R., & Bimbot, F. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2002.5743811 · Cited by 40 · see citing works
The effect of speech and audio compression on speech recognition performance
Besacier, L., Bergamini, C., Vaufreydaz, D., et al. (2002) · IEEE Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2001.962750 · Cited by 37 · see citing works
Self-citationSpeaker verification with GSM coded telephone speech
Kuitert, M., & Boves, L. (1997) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.1997-340 · Cited by 22 · see citing works
Solutions for robust recognition over the GSM cellular network
Karray, L., Jelloun, A. B., & Mokbel, C. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1998.674417 · Cited by 22 · see citing works
Ben, Blouet, & Bimbot (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2002.1005833 · Cited by 20 · see citing works
Dufour, S., Glorion, C., & Lockwood, P. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1996.540294 · Cited by 19 · see citing works
Recovering Of Packet Loss For Distributed Speech Recognition
Mayorga, P. P., Lamy, R., & Besacier, L. (2002) · doi:10.5281/zenodo.38036 · Cited by 17 · see citing works
Self-citationThe ELISA Systems for the NIST'99 Evaluation in Speaker Detection and Tracking
(2000) · Digital Signal Processing · doi:10.1006/dspr.1999.0365 · Cited by 15 · see citing works
Distributed speaker recognition using the ETSI distributed speech recognition standard
Broun, C. C. (2001) · Cited by 12 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A study on data augmentation in voice anti-spoofing
Cohen, A., Rimon, I., Aflalo, E., & Permuter, H. H. (2022) · Speech Communication · doi:10.1016/j.specom.2022.04.005 · Cited by 60 · see citing works
Benchmarking Audio Deepfake Detection Robustness in Real-World Communication Scenarios
Shi, H., Shi, X., Dogan, S., Alzubi, S., Huang, T., & Zhang, Y. (2025) · 2025 33rd European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226601 · Cited by 8 · see citing works
“Prior studies indicate that channel-induced data loss degrades the performance of audio-based feature systems [28], while codec-induced compression artifacts result in diminished audio quality as high-frequency information is lost [29], which reduces the robustness of the ADD system.”
- Authors
- Besacier, L., Mayorga, P., Bonastre, J.-F., Fredouille, C., & Meignier, S.
- Affiliations
- Université Joseph Fourier (FR)
- Université d'Avignon et des Pays de Vaucluse (FR)
- Venue
- IEE Proceedings - Vision, Image, and Signal Processing
- Published
- 2003
- Volume
- 150
- Issue
- 6
- Pages
- 372
- ISSN
- 1350-245X (ISSN-L)
- OpenAlex
- W2059187471
- Cited by
- 17
- References
- 19
- Citations by year
- 2025: 1 · 2022: 1 · 2021: 1 · 2019: 1 · 2016: 3 · 2015: 2 · 2014: 2
- FWCI
- 0.71
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEE Proceedings - Vision Image and Signal Processing (publishedVersion)
- HAL (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Keywords
- voice biometrics, speech coding, packet loss, speaker recognition, cellular networks, IP networks, low bit rate speech, speaker verification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
