Abstract
In this paper, we develop more fully all-pole modeling of speech based on the Minimum Variance Distortionless Response (MVDR) spectrum. It is shown that MVDR modeling provides a class of all-pole models that are flexible for tackling a wide variety of speech modeling objectives. In particular, the high order MVDR spectrum provides a robust model for all types of speech including voiced speech, un-voiced speech, and mixed spectra. Furthermore, it is simply obtained, and is always superior to the Linear Prediction (LP) spectrum. With its high quality modeling, the high order MVDR spectrum is suitable for use as a high quality reference spectrum, or for applications like speech recognition. In addition, the MVDR model possesses flexibility for developing low order all-pole models suitable for compression applications. In particular, Reduced Order MVDR all-pole models are shown to often outperform conventional LP filters in modeling all types of speech spectra. For more accurate modeling of a set of speech spectral samples in the frequency domain, MVDR modeling facilitates the development of superior Weighted All-Pole filters.
| Original language | English (US) |
|---|---|
| Title of host publication | Conference Record of the Asilomar Conference on Signals, Systems and Computers |
| Editors | M.P. Farques, R.D. Hippenstiel |
| Publisher | IEEE Comp Soc |
| Pages | 1061-1065 |
| Number of pages | 5 |
| Volume | 2 |
| State | Published - 1998 |
| Externally published | Yes |
| Event | Proceedings of the 1997 31st Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2) - Pacific Grove, CA, USA Duration: Nov 2 1997 → Nov 5 1997 |
Other
| Other | Proceedings of the 1997 31st Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2) |
|---|---|
| City | Pacific Grove, CA, USA |
| Period | 11/2/97 → 11/5/97 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Signal Processing
- Electrical and Electronic Engineering
Cite this
All-pole modeling of speech based on the minimum variance distortionless response spectrum. / Murthi, Manohar; Rao, Bhaskar D.
Conference Record of the Asilomar Conference on Signals, Systems and Computers. ed. / M.P. Farques; R.D. Hippenstiel. Vol. 2 IEEE Comp Soc, 1998. p. 1061-1065.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - All-pole modeling of speech based on the minimum variance distortionless response spectrum
AU - Murthi, Manohar
AU - Rao, Bhaskar D.
PY - 1998
Y1 - 1998
N2 - In this paper, we develop more fully all-pole modeling of speech based on the Minimum Variance Distortionless Response (MVDR) spectrum. It is shown that MVDR modeling provides a class of all-pole models that are flexible for tackling a wide variety of speech modeling objectives. In particular, the high order MVDR spectrum provides a robust model for all types of speech including voiced speech, un-voiced speech, and mixed spectra. Furthermore, it is simply obtained, and is always superior to the Linear Prediction (LP) spectrum. With its high quality modeling, the high order MVDR spectrum is suitable for use as a high quality reference spectrum, or for applications like speech recognition. In addition, the MVDR model possesses flexibility for developing low order all-pole models suitable for compression applications. In particular, Reduced Order MVDR all-pole models are shown to often outperform conventional LP filters in modeling all types of speech spectra. For more accurate modeling of a set of speech spectral samples in the frequency domain, MVDR modeling facilitates the development of superior Weighted All-Pole filters.
AB - In this paper, we develop more fully all-pole modeling of speech based on the Minimum Variance Distortionless Response (MVDR) spectrum. It is shown that MVDR modeling provides a class of all-pole models that are flexible for tackling a wide variety of speech modeling objectives. In particular, the high order MVDR spectrum provides a robust model for all types of speech including voiced speech, un-voiced speech, and mixed spectra. Furthermore, it is simply obtained, and is always superior to the Linear Prediction (LP) spectrum. With its high quality modeling, the high order MVDR spectrum is suitable for use as a high quality reference spectrum, or for applications like speech recognition. In addition, the MVDR model possesses flexibility for developing low order all-pole models suitable for compression applications. In particular, Reduced Order MVDR all-pole models are shown to often outperform conventional LP filters in modeling all types of speech spectra. For more accurate modeling of a set of speech spectral samples in the frequency domain, MVDR modeling facilitates the development of superior Weighted All-Pole filters.
UR - http://www.scopus.com/inward/record.url?scp=0031648998&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031648998&partnerID=8YFLogxK
M3 - Conference contribution
VL - 2
SP - 1061
EP - 1065
BT - Conference Record of the Asilomar Conference on Signals, Systems and Computers
A2 - Farques, M.P.
A2 - Hippenstiel, R.D.
PB - IEEE Comp Soc
ER -