Abstract
We propose a novel bandwidth expansion algorithm for extending narrowband speech signal to wideband by exploiting segment examples pre-stored in a speaker independent database. Both narrowband and wideband representation of speech signals are pre-stored in the corpus and they are dynamically chopped into variable length segments. Narrowband segments are used dynamically to explain a given narrowband input sentence while the wideband expanded version of the input sentence is constructed correspondingly. The matching process in the narrowband favors a longer segment patch by the chosen Maximum A Posterior (MAP) criterion. As a result, the multiple choices in matching process are significantly reduced with the MAP criterion in decoding. The approach is further generalized to deal with noise corrupted narrowband input signals and the well-known Vector Taylor Series (VTS) noise adaptation algorithm is incorporated into the matching and bandwidth expansion process. A series of experiments is performed to validate the approach on both clean and noise corrupted narrowband speech where both car noise and babble noise corrupted samples are tested.
| Original language | English |
|---|---|
| Title of host publication | 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 6087-6091 |
| Number of pages | 5 |
| ISBN (Print) | 9781479928927 |
| DOIs | |
| Publication status | Published - 2014 Jan 1 |
| Event | 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy Duration: 2014 May 4 → 2014 May 9 |
Other
| Other | 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 |
|---|---|
| Country | Italy |
| City | Florence |
| Period | 14/5/4 → 14/5/9 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Signal Processing
- Electrical and Electronic Engineering
Cite this
}
A maximum a Posterior-based reconstruction approach to speech bandwidth expansion in noise. / Seo, Hyunson; Kang, Hong Goo; Soong, Frank.
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 6087-6091 6854773.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - A maximum a Posterior-based reconstruction approach to speech bandwidth expansion in noise
AU - Seo, Hyunson
AU - Kang, Hong Goo
AU - Soong, Frank
PY - 2014/1/1
Y1 - 2014/1/1
N2 - We propose a novel bandwidth expansion algorithm for extending narrowband speech signal to wideband by exploiting segment examples pre-stored in a speaker independent database. Both narrowband and wideband representation of speech signals are pre-stored in the corpus and they are dynamically chopped into variable length segments. Narrowband segments are used dynamically to explain a given narrowband input sentence while the wideband expanded version of the input sentence is constructed correspondingly. The matching process in the narrowband favors a longer segment patch by the chosen Maximum A Posterior (MAP) criterion. As a result, the multiple choices in matching process are significantly reduced with the MAP criterion in decoding. The approach is further generalized to deal with noise corrupted narrowband input signals and the well-known Vector Taylor Series (VTS) noise adaptation algorithm is incorporated into the matching and bandwidth expansion process. A series of experiments is performed to validate the approach on both clean and noise corrupted narrowband speech where both car noise and babble noise corrupted samples are tested.
AB - We propose a novel bandwidth expansion algorithm for extending narrowband speech signal to wideband by exploiting segment examples pre-stored in a speaker independent database. Both narrowband and wideband representation of speech signals are pre-stored in the corpus and they are dynamically chopped into variable length segments. Narrowband segments are used dynamically to explain a given narrowband input sentence while the wideband expanded version of the input sentence is constructed correspondingly. The matching process in the narrowband favors a longer segment patch by the chosen Maximum A Posterior (MAP) criterion. As a result, the multiple choices in matching process are significantly reduced with the MAP criterion in decoding. The approach is further generalized to deal with noise corrupted narrowband input signals and the well-known Vector Taylor Series (VTS) noise adaptation algorithm is incorporated into the matching and bandwidth expansion process. A series of experiments is performed to validate the approach on both clean and noise corrupted narrowband speech where both car noise and babble noise corrupted samples are tested.
UR - http://www.scopus.com/inward/record.url?scp=84905226964&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84905226964&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2014.6854773
DO - 10.1109/ICASSP.2014.6854773
M3 - Conference contribution
SN - 9781479928927
SP - 6087
EP - 6091
BT - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PB - Institute of Electrical and Electronics Engineers Inc.
ER -