### Table 4. Code transformations

"... In PAGE 9: ... Each application was initially parallelized using base parallelization of loops and automatic load-store placement. Table4 lists the additional transformations that were then used. The first three are simple and can be automated; the second three are complex, requiring manual programming.... ..."

### Table 5: Comparison of MLLR and Basis Transform adapta- tion (unsupervised adaptation)

1999

"... In PAGE 3: ... We then experimented with unsupervised transcription-based adaptation done on each sentence of the same test set. The results, in Table5 , again show that the basis-transform ap- proach and MLLR give the same results. The advantage of... ..."

Cited by 2

### Table 5: Comparison of MLLR and Basis Transform adapta- tion (unsupervised adaptation)

1999

"... In PAGE 3: ... We then experimented with unsupervised transcription-based adaptation done on each sentence of the same test set. The results, in Table5 , again show that the basis-transform ap- proach and MLLR give the same results. The advantage of... ..."

Cited by 2

### Table 5: Comparison of MLLR and Basis Transform adapta- tion (unsupervised adaptation)

1999

"... In PAGE 3: ... We then experimented with unsupervised transcription-based adaptation done on each sentence of the same test set. The results, in Table5 , again show that the basis-transform ap- proach and MLLR give the same results. The advantage of... ..."

Cited by 2

### Table 1. Comparison based on equation (6) for adaptive wavelet design of nonsubsampled wavelet transform, adaptive wavelet design of orthogonal wavelet transform and Daubechies wavelet(D12).

2002

"... In PAGE 3: ... It has been verified in our experiment that equation (6) is closely proportional to the detection performance, that is, larger value corresponds to more accurate and easier detection of fabric defects. Comparison based on this criterion for adaptive wavelet design of nonsubsampled wavelet transform, adaptive wavelet design of orthogonal wavelet transform and Daubechies wavelet is shown in Table1 . The filter length of the quadrature mirror filter for adaptive wavelet in orthogonal wavelet transform is 12, and we choose the detail space in which the value of equation (6) is larger than the other two detail spaces.... ..."

Cited by 2

### Table 1. STI transformations to apply to code regions A and B based on code characteristics

"... In PAGE 4: ... The loop transformations presented above are used based upon the code characteristics which determine software pipelining effec- tiveness. Table1 presents which transformations to use for a certain combination of code regions A and B. SWP-Poor loops and acyclic code are the best candidates for STI, as these typically have ex- tra execution resources.... ..."

### Table 1: Summary of modern speech coding techniques. [2]

"... In PAGE 1: ... The short-term view is based on time- varying properties caused by the mechanical properties of the vocal tract, and leads to short-term stationary statistical models best exploited through adaptive coding strategies such as Adaptive DPCM (ADPCM) and LPC. Table1 summarizes many of the common speech coding methods. Missing abbreviations: adaptive delta modulation (ADM), adaptive transform coder (ATC), adaptive predictive coder... ..."

### Table 1: Summary of modern speech coding techniques. [2]

"... In PAGE 1: ... The short-term view is based on time- varying properties caused by the mechanical properties of the vocal tract, and leads to short-term stationary statistical models best exploited through adaptive coding strategies such as Adaptive DPCM (ADPCM) and LPC. Table1 summarizes many of the common speech coding methods. Missing abbreviations: adaptive delta modulation (ADM), adaptive transform coder (ATC), adaptive predictive coder... ..."

### Table 4. Code transformations

2005

"... In PAGE 4: ... Because many researchers are very familiar with the applications in SPEC2000, we are very specific, even listing the names of subroutines and variables within each application. Table4 shows the TLS techniques that were utilized to expose parallelism in each application. These techniques were incrementally added, and they built upon each other to generate the final speedup.... ..."

Cited by 17

### Table 3. Coding results of different transforms (PSNR in dB)

2002

"... In PAGE 4: ... Further wavelet decomposition is also applied to the DC subband of the LPPUFB and the DCT results to obtain fair comparison with the 9/7 wavelet-based encoder. The objective coding results for some test images are given in Table3 , which show that for smooth images like Lena and Gold- hill, the performance of the LPPUFB without DC leakage is com- parable with the wavelet, but for highly-textured images like Bar- bara, the LPPUFB can outperform the wavelet by as much as 2dB. The LPPUFB with PMI property could not eliminate the DC leakage.... ..."

Cited by 1