A data-driven speech enhancement method based on A longest segment searching technique
This paper proposed a data-driven speech enhancement method based on the modeled long-range temporal dynamics (LRTDs). First, by extracting the Mel-Frequency Cepstral coefficient (MFCC) features from speech and noise corpora, the Gaussian Mixture Models (GMMs) of the speech and noise were trained re...
Saved in:
| Published in | Speech communication Vol. 92; pp. 142 - 151 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.09.2017
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0167-6393 1872-7182 |
| DOI | 10.1016/j.specom.2017.06.004 |
Cover
| Abstract | This paper proposed a data-driven speech enhancement method based on the modeled long-range temporal dynamics (LRTDs). First, by extracting the Mel-Frequency Cepstral coefficient (MFCC) features from speech and noise corpora, the Gaussian Mixture Models (GMMs) of the speech and noise were trained respectively based on the expectation-maximization (EM) algorithm. Then, the LRTDs were obtained from the GMM models. Next, based on the LRTDs, a modified maximum a posterior (MAP) based adaptive longest matching segment searching (ALMSS) method derived from A* search technique was combined with the Vector Taylor Series (VTS) approximation algorithm in order to search the longest matching speech and noise segments (LMSNS) from speech and noise corpora. Finally, using the obtained LMSNS, the estimation of speech spectrum was achieved. Furthermore, a modified Wiener filter was constructed to further eliminate residual noise. The objective and subjective test results show that the proposed method outperforms the reference methods. |
|---|---|
| AbstractList | This paper proposed a data-driven speech enhancement method based on the modeled long-range temporal dynamics (LRTDs). First, by extracting the Mel-Frequency Cepstral coefficient (MFCC) features from speech and noise corpora, the Gaussian Mixture Models (GMMs) of the speech and noise were trained respectively based on the expectation-maximization (EM) algorithm. Then, the LRTDs were obtained from the GMM models. Next, based on the LRTDs, a modified maximum a posterior (MAP) based adaptive longest matching segment searching (ALMSS) method derived from A* search technique was combined with the Vector Taylor Series (VTS) approximation algorithm in order to search the longest matching speech and noise segments (LMSNS) from speech and noise corpora. Finally, using the obtained LMSNS, the estimation of speech spectrum was achieved. Furthermore, a modified Wiener filter was constructed to further eliminate residual noise. The objective and subjective test results show that the proposed method outperforms the reference methods. |
| Author | Hao, Yue Bao, Changchun Bao, Feng |
| Author_xml | – sequence: 1 givenname: Yue surname: Hao fullname: Hao, Yue organization: Speech and Audio Signal Processing Lab, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China – sequence: 2 givenname: Feng surname: Bao fullname: Bao, Feng organization: Department of Electrical and Computer Engineering, The University of Auckland, Auckland 1010, New Zealand – sequence: 3 givenname: Changchun surname: Bao fullname: Bao, Changchun email: baochch@bjut.edu.cn organization: Speech and Audio Signal Processing Lab, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China |
| BookMark | eNp9kM1KAzEUhYNUsK2-gYu8wIzJ_CQzG6EU_6DgRt2GTHLTSekkNYkF397UunZ14XC-wz1ngWbOO0DolpKSEsrudmU8gPJTWRHKS8JKQpoLNKcdrwpOu2qG5tnGC1b39RVaxLgj2dF11Rx9rLCWSRY62CM4nHNAjRjcKJ2CCVzCE6TRazzICBp7h1d4790WYsIRtr-OCDKo0botThl29vMLrtGlkfsIN393id4fH97Wz8Xm9ellvdoUqmrbVJiBypryllJDaA8N4Y1sa6W46aBrGEjaq3ZQhrIBiG6kMZIr1pOKkSyqql6i5pyrgo8xgBGHYCcZvgUl4rSN2InzNuK0jSBM5OYZuz9jkH87WggiKgu5sbYBVBLa2_8DfgC9L3JS |
| Cites_doi | 10.1109/TASLP.2016.2636445 10.1109/TASSP.1979.1163209 10.1038/44565 10.1109/TSA.2005.851929 10.1111/j.2517-6161.1977.tb01600.x 10.1109/TASL.2010.2064312 10.1109/TASL.2006.885256 10.1109/PROC.1979.11540 10.1109/TASLP.2015.2458585 10.1109/TASSP.1980.1163420 10.1109/TASSP.1984.1164453 10.1109/TASL.2009.2031793 10.1109/TASL.2013.2250959 10.1016/0167-6393(93)90095-3 10.1109/97.988717 |
| ContentType | Journal Article |
| Copyright | 2017 Elsevier B.V. |
| Copyright_xml | – notice: 2017 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.specom.2017.06.004 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Languages & Literatures Social Welfare & Social Work Psychology |
| EISSN | 1872-7182 |
| EndPage | 151 |
| ExternalDocumentID | 10_1016_j_specom_2017_06_004 S0167639316302540 |
| GroupedDBID | --K --M -~X .DC .~1 07C 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN 9JO AACTN AADFP AAEDT AAEDW AAFJI AAGJA AAGJQ AAGUQ AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABIVO ABJNI ABMAC ABMMH ABOYX ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACXNI ACZNC ADBBV ADEZE ADIYS ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AFYLN AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AKYCK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOMHK AOUOD ASPBG AVARZ AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 M41 MO0 N9A O-L O9- OAUVE OKEIE OZT P-8 P-9 P2P PC. PQQKQ PRBVW Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SSB SSO SST SSV SSY SSZ T5K WUQ XFK XJE ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c255t-fb1a317511f019e4074a53cc7f8e846ea19c5bcf16be0d4affa7c690260cf1c23 |
| IEDL.DBID | AIKHN |
| ISSN | 0167-6393 |
| IngestDate | Thu Jul 03 08:30:31 EDT 2025 Fri Feb 23 02:28:30 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | A search technique VTS ALMSS GMM Modified Wiener filter Speech enhancement LRTDs |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c255t-fb1a317511f019e4074a53cc7f8e846ea19c5bcf16be0d4affa7c690260cf1c23 |
| PageCount | 10 |
| ParticipantIDs | crossref_primary_10_1016_j_specom_2017_06_004 elsevier_sciencedirect_doi_10_1016_j_specom_2017_06_004 |
| PublicationCentury | 2000 |
| PublicationDate | September 2017 2017-09-00 |
| PublicationDateYYYYMMDD | 2017-09-01 |
| PublicationDate_xml | – month: 09 year: 2017 text: September 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | Speech communication |
| PublicationYear | 2017 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Ming (bib0010) 2009 Acero, Deng, Kristjansson, Zhang (bib0015) 2000; 3 Gao, Bao, Bao, Jia (bib0008) 2014 Cohen (bib0021) 2002; 9 Gopalakrishnan, Bahl, Mercer (bib0019) 1995 Davis, Mermelstein (bib0013) 1980 Hao, Bao, Bao, Deng (bib0012) 2015 Xiao, Nickel (bib0009) 2010; 18 Ming, Srinivasan, Crookes, Jafari (bib0020) 2013; 27 Srinivasan, Samuelsson, Klejin (bib0005) 2007; 15 Loizou (bib0004) 2005; 13 Bao, Jing, Jia, Bao (bib0017) 2014 Lim, Oppenheim (bib0001) 1979; 67 Varga, Steeneken (bib0100) 1993; 12 He, Bao, Bao (bib0027) 2017; 25 Zhao, Kleijn (bib0007) 2007; 15 Abramson, Cohen (bib0023) 2007; 15 Dempster, Laird, Rubin (bib0014) 1977; 39 Ming, Crookes (bib0011) 2011; 19 Paul (bib0018) 1995 Quackenbush, Barnwell, Clements (bib0022) 1988 Ephraim, Malah (bib0003) 1984; 32 Deng, Bao, Kleijin (bib0026) 2015; 23 Lee, Seung (bib0006) 1999 Ogawa, Kinoshita, Hori, Nakatani (bib0016) 2014 Boll (bib0002) 1979; 27 Vincent (bib0025) 2005 Cohen (10.1016/j.specom.2017.06.004_bib0021) 2002; 9 Bao (10.1016/j.specom.2017.06.004_bib0017) 2014 Gao (10.1016/j.specom.2017.06.004_bib0008) 2014 Abramson (10.1016/j.specom.2017.06.004_bib0023) 2007; 15 Quackenbush (10.1016/j.specom.2017.06.004_bib0022) 1988 Boll (10.1016/j.specom.2017.06.004_bib0002) 1979; 27 Dempster (10.1016/j.specom.2017.06.004_bib0014) 1977; 39 Ming (10.1016/j.specom.2017.06.004_bib0011) 2011; 19 Gopalakrishnan (10.1016/j.specom.2017.06.004_bib0019) 1995 Zhao (10.1016/j.specom.2017.06.004_bib0007) 2007; 15 Ming (10.1016/j.specom.2017.06.004_bib0010) 2009 Varga (10.1016/j.specom.2017.06.004_bib0100) 1993; 12 Davis (10.1016/j.specom.2017.06.004_bib0013) 1980 Loizou (10.1016/j.specom.2017.06.004_bib0004) 2005; 13 Ephraim (10.1016/j.specom.2017.06.004_bib0003) 1984; 32 Paul (10.1016/j.specom.2017.06.004_bib0018) 1995 Deng (10.1016/j.specom.2017.06.004_bib0026) 2015; 23 Srinivasan (10.1016/j.specom.2017.06.004_bib0005) 2007; 15 Ming (10.1016/j.specom.2017.06.004_bib0020) 2013; 27 He (10.1016/j.specom.2017.06.004_bib0027) 2017; 25 Lee (10.1016/j.specom.2017.06.004_bib0006) 1999 Vincent (10.1016/j.specom.2017.06.004_bib0025) Acero (10.1016/j.specom.2017.06.004_bib0015) 2000; 3 Hao (10.1016/j.specom.2017.06.004_bib0012) 2015 Ogawa (10.1016/j.specom.2017.06.004_bib0016) 2014 Lim (10.1016/j.specom.2017.06.004_bib0001) 1979; 67 Xiao (10.1016/j.specom.2017.06.004_bib0009) 2010; 18 |
| References_xml | – start-page: 572 year: 1995 end-page: 575 ident: bib0019 article-title: A tree search strategy for large-vocabulary continuous speech recognition publication-title: Proc. ICASSP – year: 1988 ident: bib0022 article-title: Objective Measures of Speech Quality – volume: 23 start-page: 1973 year: 2015 end-page: 1987 ident: bib0026 article-title: Sparse hidden Markov models for speech enhancement in non-stationary noise environments publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. – volume: 9 start-page: 12 year: 2002 end-page: 15 ident: bib0021 article-title: Noise estimation by minima controlled recursive averaging for robust speech enhancement publication-title: IEEE Signal Process. Lett. – start-page: 1557 year: 2014 end-page: 1561 ident: bib0016 article-title: Fast segment search for corpus-based speech enhancement based on speech recognition technology publication-title: Proc. ICASSP – start-page: 733 year: 2014 end-page: 737 ident: bib0008 article-title: HMM-based speech enhancement using vector Taylor series and parallel modeling in mel-frequency domain publication-title: IEEE International Conference on Signal Processing, Communications & Computing (ICSPCC) – volume: 15 start-page: 441 year: 2007 end-page: 451 ident: bib0005 article-title: Codebook-based Bayesian speech enhancement for nonstationary environments publication-title: IEEE Trans. Acoust. Speech Signal Process. – volume: 3 start-page: 229 year: 2000 end-page: 232 ident: bib0015 article-title: HMM adaptation using vector Taylor series for noisy speech recognition publication-title: ICSLP – volume: 32 start-page: 1109 year: 1984 end-page: 1121 ident: bib0003 article-title: Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator publication-title: IEEE Trans. Acoust. Speech Signal Process. – volume: 67 start-page: 1586 year: 1979 end-page: 1604 ident: bib0001 article-title: Enhancement and bandwidth compression of noisy speech publication-title: Proc. IEEE. – volume: 15 start-page: 882 year: 2007 end-page: 892 ident: bib0007 article-title: HMM-based gain modeling for enhancement of speech in noise publication-title: IEEE Trans. Audio Speech Lang. Process. – volume: 25 start-page: 457 year: 2017 end-page: 468 ident: bib0027 article-title: Multiplicative update of auto-regressive gains for codebook-based speech enhancement publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. – start-page: 90 year: 2014 end-page: 94 ident: bib0017 article-title: Speech enhancement based on a few shapes of speech spectrum publication-title: IEEE CHINASIP – volume: 13 start-page: 857 year: 2005 end-page: 869 ident: bib0004 article-title: Speech enhancement based on perceptually motivated Bayesian estimators of the magnitude spectrum publication-title: IEEE Trans. Acoust. Speech Signal Process. – volume: 18 start-page: 1254 year: 2010 end-page: 1257 ident: bib0009 article-title: Speech enhancement with inventory style speech resynthesis publication-title: IEEE Trans. Audio Speech Lang. Process. – start-page: 45 year: 1995 end-page: 48 ident: bib0018 article-title: New developments in the Lincoln stack-decoder based large-vocabulary CSR system publication-title: Proc. ICASSP – volume: 27 start-page: 113 year: 1979 end-page: 120 ident: bib0002 article-title: Suppression of acoustic noise in speech using spectral subtraction publication-title: IEEE Trans. Acoust. Speech Signal Process. – year: 1999 ident: bib0006 article-title: Learning the parts of objects by non-negative matrix factorization publication-title: Nature – volume: 15 start-page: 2348 year: 2007 end-page: 2359 ident: bib0023 article-title: Simultaneous detection and estimation approach for speech enhancement publication-title: IEEE Trans. Acoust. Speech Signal Process. – start-page: 357 year: 1980 end-page: 365 ident: bib0013 article-title: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences publication-title: IEEE Trans. Acoust. Speech Signal Process. – volume: 39 start-page: 1 year: 1977 end-page: 38 ident: bib0014 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J. R. Stat. Soc. Ser. B. – start-page: 1790 year: 2015 end-page: 1794 ident: bib0012 article-title: A data-driven speech enhancement method based on long-range temporal dynamics publication-title: Interspeech – start-page: 3849 year: 2009 end-page: 3852 ident: bib0010 article-title: Maximizing the continuity in segmentation-a new approach to model, segment and recognize speech publication-title: Proc. ICASSP. – volume: 12 start-page: 247 year: 1993 end-page: 251 ident: bib0100 article-title: Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems publication-title: Speech Commun. – year: 2005 ident: bib0025 article-title: MUSHRAM: A MATLAB interface for MUSHRA listening tests – volume: 27 start-page: 1355 year: 2013 end-page: 1368 ident: bib0020 article-title: CLOSE-a data-driven approach to speech separation publication-title: IEEE Trans. Audio Speech Lang. Process. – volume: 19 start-page: 822 year: 2011 end-page: 836 ident: bib0011 article-title: A corpus-based approach to speech enhancement from nonstationary noise publication-title: IEEE Trans. Speech Audio Process. – volume: 25 start-page: 457 issue: 3 year: 2017 ident: 10.1016/j.specom.2017.06.004_bib0027 article-title: Multiplicative update of auto-regressive gains for codebook-based speech enhancement publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2016.2636445 – volume: 27 start-page: 113 issue: 2 year: 1979 ident: 10.1016/j.specom.2017.06.004_bib0002 article-title: Suppression of acoustic noise in speech using spectral subtraction publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/TASSP.1979.1163209 – year: 1999 ident: 10.1016/j.specom.2017.06.004_bib0006 article-title: Learning the parts of objects by non-negative matrix factorization publication-title: Nature doi: 10.1038/44565 – volume: 13 start-page: 857 issue: 5 year: 2005 ident: 10.1016/j.specom.2017.06.004_bib0004 article-title: Speech enhancement based on perceptually motivated Bayesian estimators of the magnitude spectrum publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/TSA.2005.851929 – volume: 39 start-page: 1 issue: 1 year: 1977 ident: 10.1016/j.specom.2017.06.004_bib0014 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J. R. Stat. Soc. Ser. B. doi: 10.1111/j.2517-6161.1977.tb01600.x – start-page: 733 year: 2014 ident: 10.1016/j.specom.2017.06.004_bib0008 article-title: HMM-based speech enhancement using vector Taylor series and parallel modeling in mel-frequency domain – volume: 19 start-page: 822 issue: 4 year: 2011 ident: 10.1016/j.specom.2017.06.004_bib0011 article-title: A corpus-based approach to speech enhancement from nonstationary noise publication-title: IEEE Trans. Speech Audio Process. doi: 10.1109/TASL.2010.2064312 – volume: 15 start-page: 2348 issue: 8 year: 2007 ident: 10.1016/j.specom.2017.06.004_bib0023 article-title: Simultaneous detection and estimation approach for speech enhancement publication-title: IEEE Trans. Acoust. Speech Signal Process. – start-page: 1557 year: 2014 ident: 10.1016/j.specom.2017.06.004_bib0016 article-title: Fast segment search for corpus-based speech enhancement based on speech recognition technology – volume: 15 start-page: 441 issue: 2 year: 2007 ident: 10.1016/j.specom.2017.06.004_bib0005 article-title: Codebook-based Bayesian speech enhancement for nonstationary environments publication-title: IEEE Trans. Acoust. Speech Signal Process. – volume: 15 start-page: 882 issue: 3 year: 2007 ident: 10.1016/j.specom.2017.06.004_bib0007 article-title: HMM-based gain modeling for enhancement of speech in noise publication-title: IEEE Trans. Audio Speech Lang. Process. doi: 10.1109/TASL.2006.885256 – volume: 67 start-page: 1586 issue: 12 year: 1979 ident: 10.1016/j.specom.2017.06.004_bib0001 article-title: Enhancement and bandwidth compression of noisy speech publication-title: Proc. IEEE. doi: 10.1109/PROC.1979.11540 – volume: 23 start-page: 1973 issue: 11 year: 2015 ident: 10.1016/j.specom.2017.06.004_bib0026 article-title: Sparse hidden Markov models for speech enhancement in non-stationary noise environments publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2015.2458585 – start-page: 357 year: 1980 ident: 10.1016/j.specom.2017.06.004_bib0013 article-title: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/TASSP.1980.1163420 – volume: 32 start-page: 1109 issue: 6 year: 1984 ident: 10.1016/j.specom.2017.06.004_bib0003 article-title: Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/TASSP.1984.1164453 – volume: 18 start-page: 1254 issue: 6 year: 2010 ident: 10.1016/j.specom.2017.06.004_bib0009 article-title: Speech enhancement with inventory style speech resynthesis publication-title: IEEE Trans. Audio Speech Lang. Process. doi: 10.1109/TASL.2009.2031793 – ident: 10.1016/j.specom.2017.06.004_bib0025 – volume: 27 start-page: 1355 year: 2013 ident: 10.1016/j.specom.2017.06.004_bib0020 article-title: CLOSE-a data-driven approach to speech separation publication-title: IEEE Trans. Audio Speech Lang. Process. doi: 10.1109/TASL.2013.2250959 – volume: 12 start-page: 247 issue: 3 year: 1993 ident: 10.1016/j.specom.2017.06.004_bib0100 article-title: Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems publication-title: Speech Commun. doi: 10.1016/0167-6393(93)90095-3 – start-page: 572 year: 1995 ident: 10.1016/j.specom.2017.06.004_bib0019 article-title: A tree search strategy for large-vocabulary continuous speech recognition – start-page: 3849 year: 2009 ident: 10.1016/j.specom.2017.06.004_bib0010 article-title: Maximizing the continuity in segmentation-a new approach to model, segment and recognize speech – volume: 9 start-page: 12 issue: 1 year: 2002 ident: 10.1016/j.specom.2017.06.004_bib0021 article-title: Noise estimation by minima controlled recursive averaging for robust speech enhancement publication-title: IEEE Signal Process. Lett. doi: 10.1109/97.988717 – volume: 3 start-page: 229 year: 2000 ident: 10.1016/j.specom.2017.06.004_bib0015 article-title: HMM adaptation using vector Taylor series for noisy speech recognition publication-title: ICSLP – start-page: 90 year: 2014 ident: 10.1016/j.specom.2017.06.004_bib0017 article-title: Speech enhancement based on a few shapes of speech spectrum – start-page: 1790 year: 2015 ident: 10.1016/j.specom.2017.06.004_bib0012 article-title: A data-driven speech enhancement method based on long-range temporal dynamics – year: 1988 ident: 10.1016/j.specom.2017.06.004_bib0022 – start-page: 45 year: 1995 ident: 10.1016/j.specom.2017.06.004_bib0018 article-title: New developments in the Lincoln stack-decoder based large-vocabulary CSR system |
| SSID | ssj0004882 |
| Score | 2.166075 |
| Snippet | This paper proposed a data-driven speech enhancement method based on the modeled long-range temporal dynamics (LRTDs). First, by extracting the Mel-Frequency... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 142 |
| SubjectTerms | A search technique ALMSS GMM LRTDs Modified Wiener filter Speech enhancement VTS |
| Title | A data-driven speech enhancement method based on A longest segment searching technique |
| URI | https://dx.doi.org/10.1016/j.specom.2017.06.004 |
| Volume | 92 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED6VdmFBUF6FgjwgtlAc59GOVUVVoLDw3KLEPkOhSqq0DCz8dnyJU0BIDIw52ZF1tu5hf98dwFESSqEFBg5XriRKjna6iaccJZSHvtDcLerMXl0Hozvv4tF_rMGg4sIQrNLa_tKmF9baSjpWm53ZZNK5IQC98a_CRBRE6TZ5e8MVvcCvQ6N_fjm6_qJHdoueUUWJb5pQMegKmBcRGjOipPOwKORpO7b98lDfvM5wHdZsuMj65Yo2oIZpE3bG9pJxzo7ZeFkXed6E1aU9e29Cu6Tesgec6jhHM7YSZPnrJtz3GcFDHZWTwWNmhSifGabPdA7ozpCV3aUZOTrFspT12TRL6T2KzfGpGGEfItIntqwFuwV3w7PbwcixXRYcadKJhaMTHlMQwbk24R6aBM-LfSFlqLtoghOMeU_6idQ8SPBUebHWcShNTm0SISOUrtiGepqluAssDEw6ZH7BeRh4vKvo0TZJtELOUeCpaIFTaTaalcU0ogpl9hKVOxHRTkQF2M5rQVipP_pxKCJj7_-cuffvmfuwSl8ljKwN9UX-hgcm7lgkh7By8sEP7en6BJWT1_4 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED5VMMCCoLyfHhBbaF3nUcaqoirQdqFAtyixz7SAEtSWgYXfzl0eBYTEwOrYkXU-3cP3fWeA0zjQyir0HWkamik51mnGrnGMMi56yspG1me2P_C7d-71yBtVoF1yYRhWWdj-3KZn1roYqRXSrL1OJrVbBtCTf1UUUTClm_L2ZddTAeP6zj--cB6koY2ywTdPL_lzGciL6YwpE9JlkLXxLN5r--WfvvmczjqsFcGiaOX72YAKJlXY6RVXjDNxJnqLrsizKqwurNl7FQ5z4q14wBcbTZHmlgPp9HkT7luCwaGOmbK5E7RD1GOByZi1gG8MRf62tGA3Z0SaiJZ4SROuRokZPmYzijJE8igWnWC34K5zOWx3neKNBUdTMjF3bCwjDiGktBTsIaV3buQprQPbRApNMJIX2ou1lX6MdeNG1kaBpoya0iAa1A21DUtJmuAuiMCnZIh-IWXgu7JpuGQbx9aglKiwrvbAKSUbvuatNMISY_YU5icR8kmEGdTO3YOgFH_4QyVCsvZ_rtz_98oTWOkO-72wdzW4OYBV_pIDyg5haT59wyOKQObxcaZhn2YC2Mk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+data-driven+speech+enhancement+method+based+on+A+longest+segment+searching+technique&rft.jtitle=Speech+communication&rft.au=Hao%2C+Yue&rft.au=Bao%2C+Feng&rft.au=Bao%2C+Changchun&rft.date=2017-09-01&rft.pub=Elsevier+B.V&rft.issn=0167-6393&rft.eissn=1872-7182&rft.volume=92&rft.spage=142&rft.epage=151&rft_id=info:doi/10.1016%2Fj.specom.2017.06.004&rft.externalDocID=S0167639316302540 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-6393&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-6393&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-6393&client=summon |