The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

voice vignette

version 0.4.21

Filipe J. Zabala

2023-04-19

0. Installation

https://github.com/filipezabala/voice

1. Extract features

Load packages and audio files

# packs
library(voice)

# get path to audio file
wavDir <- list.files(system.file('extdata', package = 'wrassp'),
                     pattern = glob2rx('*.wav'), full.names = TRUE)

Examples

# minimal usage
M <- voice::extract_features(wavDir)
M
#> # A tibble: 1,193 × 65
#>    section_seq section_seq_file wav_path        f0    f1    f2    f3    f4    f5
#>          <int>            <int> <chr>        <dbl> <int> <int> <int> <int> <int>
#>  1           1                1 /Library/Fr…   NA     NA  1854    NA  3113  4191
#>  2           2                2 /Library/Fr…   NA     NA  1886  2893  3708  4678
#>  3           3                3 /Library/Fr…   NA     NA  1749  2676  3509  4502
#>  4           4                4 /Library/Fr…   NA     NA  1888  2659  3658  4331
#>  5           5                5 /Library/Fr…   NA    185  1962  2639  3248  3653
#>  6           6                6 /Library/Fr…   NA    260  1973  2676  3239  3836
#>  7           7                7 /Library/Fr…   NA    254  2026  2993  3830  4602
#>  8           8                8 /Library/Fr…  116.   277  2037  2932  3479  4585
#>  9           9                9 /Library/Fr…  109.   261  2130  3016  3561  4720
#> 10          10               10 /Library/Fr…  107.   231  2301  2907  3889  4818
#> # ℹ 1,183 more rows
#> # ℹ 56 more variables: f6 <int>, f7 <int>, f8 <int>, rfc1 <dbl>, rfc2 <dbl>,
#> #   rfc3 <dbl>, rfc4 <dbl>, rfc5 <dbl>, rfc6 <dbl>, rfc7 <dbl>, rfc8 <dbl>,
#> #   rfc9 <dbl>, rfc10 <dbl>, rfc11 <dbl>, rfc12 <dbl>, rfc13 <dbl>,
#> #   rfc14 <dbl>, rfc15 <dbl>, rfc16 <dbl>, rfc17 <dbl>, rfc18 <dbl>,
#> #   rfc19 <dbl>, mfcc1 <dbl>, mfcc2 <dbl>, mfcc3 <dbl>, mfcc4 <dbl>,
#> #   mfcc5 <dbl>, mfcc6 <dbl>, mfcc7 <dbl>, mfcc8 <dbl>, mfcc9 <dbl>, …

2. Tag

# creating Extended synthetic data
E <- dplyr::tibble(subject_id = c(1,1,1,2,2,2,3,3,3), wav_path = wavDir)
E
#> # A tibble: 9 × 2
#>   subject_id wav_path                                                           
#>        <dbl> <chr>                                                              
#> 1          1 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 2          1 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 3          1 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 4          2 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 5          2 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 6          2 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 7          3 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 8          3 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…
#> 9          3 /Library/Frameworks/R.framework/Versions/4.2/Resources/library/wra…

# minimal usage
voice::tag(E)
#> # A tibble: 9 × 7
#>   wav_path   f0_tag_mean f0_tag_sd f0_tag_vc f0_tag_median f0_tag_iqr f0_tag_mad
#>   <chr>            <dbl>     <dbl>     <dbl>         <dbl>      <dbl>      <dbl>
#> 1 /Library/…        85.4      17.6     0.206          76.1       29.4       7.53
#> 2 /Library/…        85.4      15.6     0.183          80.1       27.8      14.4 
#> 3 /Library/…        84.6      13.0     0.154          78.8       23.9      14.0 
#> 4 /Library/…        84.8      14.5     0.171          79.1       28.1      11.9 
#> 5 /Library/…        86.0      14.7     0.170          78.7       30.0      11.0 
#> 6 /Library/…        82.9      15.6     0.188          74.8       23.8       4.78
#> 7 /Library/…        78.2      16.2     0.207          73.5       13.4       6.82
#> 8 /Library/…        84.5      14.5     0.172          78.1       17.8       8.95
#> 9 /Library/…        81.0      12.2     0.151          75.9       23.1       9.14

# canonical data
voice::tag(E, groupBy = 'subject_id')
#> # A tibble: 3 × 7
#>   subject_id f0_tag_mean f0_tag_sd f0_tag_vc f0_tag_median f0_tag_iqr f0_tag_mad
#>        <dbl>       <dbl>     <dbl>     <dbl>         <dbl>      <dbl>      <dbl>
#> 1          1        85.1      15.3     0.180          78.3       26.8      11.9 
#> 2          2        84.6      14.9     0.176          76.4       28.3       7.97
#> 3          3        81.0      14.6     0.180          75.6       21.6       8.68

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.