CEPSTRAL PARAMETER COMPENSATION FOR HMM RECOGNITION IN NOISE

被引：85
作者：
GALES, MJF
YOUNG, SJ
机构：
[1] Cambridge University Engineering Department, Cambridge, Trumpington Street
来源：
SPEECH COMMUNICATION | 1993年 / 12卷 / 03期
关键词：
SPEECH RECOGNITION; NOISE COMPENSATION; AMN; PMC;
D O I：
10.1016/0167-6393(93)90093-Z
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper describes a method of adapting a continuous density HMM recogniser trained on clean cepstral speech data to make it robust to noise. The technique is based on parallel model combination (PMC) in which the parameters of corresponding pairs of speech and noise states are combined to yield a set of compensated parameters. It improves on earlier cepstral mean compensation methods in that it also adapts the variances and as a result can deal with much lower SNRs. The PMC method is evaluated on the NOISEX-92 noise database and shown to work well down to 0 dB SNR and below for both stationary and non-stationary noises. Furthermore, for relatively constant noise conditions, there is no additional computational cost at run-time.
引用
收藏
页码：231 / 239
页数：9
相关论文
共 24 条
  • [11] HOMES JN, 1986, P INT C ACOUST SPEEC, P741
  • [12] Juang B. H., 1991, Computer Speech and Language, V5, P275, DOI 10.1016/0885-2308(91)90011-E
  • [13] KADIRKAMANATHAN, 1992, NOV P ESCA WORKSH SP, P187
  • [14] KLATT DH, 1979, P ICASSP, P573
  • [15] EXPERIMENTS WITH A NONLINEAR SPECTRAL SUBTRACTOR (NSS), HIDDEN MARKOV-MODELS AND THE PROJECTION, FOR ROBUST SPEECH RECOGNITION IN CARS
    LOCKWOOD, P
    BOUDY, J
    [J]. SPEECH COMMUNICATION, 1992, 11 (2-3) : 215 - 228
  • [16] Mansour D., 1988, P ICASSP 88, P36
  • [17] MELLOR BA, 1992, AUT P I AC C SPEECH, V14, P361
  • [18] MOORE RK, 1986, RSRE3931 ROY SIGN RA
  • [19] Paul D. B., 1987, Proceedings: ICASSP 87. 1987 International Conference on Acoustics, Speech, and Signal Processing (Cat. No.87CH2396-0), P713
  • [20] SORENSEN HBD, 1991, P INT C AC SPEECH SI, P933
123