On artificial bandwidth extension of telephone speech

Authors:
Peter Jax;Peter Vary
Affiliations:
Institute of Communication Systems and Data Processing (IND), Aachen University (RWTH), Aachen D-52056, Germany;Institute of Communication Systems and Data Processing (IND), Aachen University (RWTH), Aachen D-52056, Germany
Venue:
Signal Processing - Special section: Hans Wilhelm Schüßler celebrates his 75th birthday
Year:
2003

Citing 3
Cited 10

Fundamentals of speech recognition

Fundamentals of speech recognition
Techniques for the regeneration of wideband speech from narrowband speech

EURASIP Journal on Applied Signal Processing - Nonlinear signal and image processing - part I
Linear Prediction of Speech

Linear Prediction of Speech

Techniques for artificial bandwidth extension of telephone speech

Signal Processing
Bandwidth extension of telephone speech aided by data embedding

EURASIP Journal on Applied Signal Processing
A study of HMM-based bandwidth extension of speech signals

Signal Processing
A codebook design method for fricative enhancement in artificial bandwidth extension

Proceedings of the 5th International ICST Mobile Multimedia Communications Conference
The SIGMA algorithm: a glottal activity detector for electroglottographic signals

IEEE Transactions on Audio, Speech, and Language Processing
AffectAura: an intelligent system for emotional memory

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Fast communication: On second-order statistics of log-periodogram and cepstral coefficients for processes with mixed spectra

Signal Processing
A HMM-WDLT framework for HNM-based voice conversion with parametric adjustment in formant bandwidth, duration and excitation

International Journal of Speech Technology
Artificial bandwidth extension of spectral envelope along a Viterbi path

Speech Communication
Superwideband bandwidth extension using normalized MDCT coefficients for scalable speech and audio coding

Advances in Multimedia - Special issue on Multimedia Applications for Smart Device in Ubiquitous Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a signal processing algorithm to convert speech signals with "standard telephone" quality into 7 kHz wideband speech. A statistical approach based on a hidden Markov model (HMM) is used, which takes into account several features of the band-limited speech. The narrowband input signal is classified into a limited number of speech sounds (HMM states) for which the wideband spectral envelope is estimated using the pre-trained model. The enhanced speech exhibits a significantly improved quality without objectionable artifacts.