A study of HMM-based bandwidth extension of speech signals

Authors:
Geun-Bae Song;Pavel Martynovich
Affiliations:
Samsung Electronics Co., Ltd., Suwon-si, Gyeonggi-do 442-742, Republic of Korea;Samsung Electronics Co., Ltd., Suwon-si, Gyeonggi-do 442-742, Republic of Korea
Venue:
Signal Processing
Year:
2009

Citing 7
Cited 1

A tutorial on hidden Markov models and selected applications in speech recognition

Readings in speech recognition
On artificial bandwidth extension of telephone speech

Signal Processing - Special section: Hans Wilhelm Schüßler celebrates his 75th birthday
On the phonetic structure of a large hidden Markov model

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
A speech spectrum distortion measure with interframe memory

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02
Predictive vector quantization of wideband LSF using narrowband LSF for bandwidth scalable coders

Speech Communication
Evaluation of an Artificial Speech Bandwidth Extension Method in Three Languages

IEEE Transactions on Audio, Speech, and Language Processing
Extended AMR-WB for high-quality audio on mobile devices

IEEE Communications Magazine

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	0.08

Visualization

Abstract

In this paper, we investigate a representative statistical method for artificial bandwidth extension: the hidden Markov model (HMM) based method. In particular, we are interested in objectively quantifying its performance using both static and dynamic measures. The Gaussian mixture model (GMM) based method is presented as a reference method for the performance test under various HMM configurations. We also reasonably claim that a general approach using Baum-Welch re-estimation algorithm performs better than the existing training algorithm suggested by Jax. Accordingly, it is used as the basic algorithm for the training of HMM model. Test results show that the static performance of HMM-based method depends only on the total number of Gaussian components of HMM model, while its dynamic performance depends dominantly on the number of states of the model. More specifically, it is also observed that the GMM-based method is quite comparable with the HMM-based one in static performance, but, in dynamic performance, the latter outperforms the former even with higher computational complexities.