`voice` vignette

In voice: Speaker Recognition, Voice Analysis and Mood Inference via Music Theory

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
ini0 <- Sys.time()

0. Basic installation

# Development version from GitHub
install.packages('devtools')
devtools::install_github('filipezabala/voice')

# Stable version from CRAN
install.packages('voice')

0.1 For Windows Users

If you're compiling R packages from source, you may need to install RTools, a collection of Windows-specific build tools for R.

0.2 For macOS Users

If you're compiling packages, ensure you have Xcode Command Line Tools installed. You also may need macOS tools.

```{bash, eval=FALSE}

Install Xcode on MacOS

xcode-select --install

More details may be found at https://github.com/filipezabala/voice.


## 1. Extract features
### 1.1 Load packages and audio files
```r
# packs
library(voice)
library(tidyverse)

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

1.2 Extract features

# minimal usage
M <- voice::extract_features(wavDir)
glimpse(M)

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

# minimal usage
voice::tag(E)

# canonical data
voice::tag(E, groupBy = 'subject_id')

3. Visualization

3.1 Get audio

url0 <- 'https://github.com/filipezabala/voiceAudios/raw/refs/heads/main/wav/doremi.wav'
download.file(url0, paste0(tempdir(), '/doremi.wav'), mode = 'wb')
voice::embed_audio(url0) # See https://github.com/mccarthy-m-g/embedr for more details.

3.2 Media data

M <- voice::extract_features(tempdir())
summary(M)

3.3 Plot

voice::piano_plot(M, 0) # f0
voice::piano_plot(M, 0:1) # f0 + f1

{width=95%} {width=95%}

3.4 Assign notes

(f0_spn <- voice::assign_notes(M, fmt = 0, min_points = 22, min_percentile = .85)) # f0
(f1_spn <- voice::assign_notes(M, fmt = 1, min_points = 22, min_percentile = .85)) # f1

3.5 Sheet music

Must have MuseScore and gm.

3.5.1 Notes sequence of f0

library(gm)
line_0 <- gm::Line(as.character(f0_spn))
m0 <- gm::Music() +
  gm::Meter(4, 4) +
  line_0
gm::show(m0, to = c('score', 'audio'))

{width=95%}

3.5.2 Notes sequences of f0 and f1

line_0 <- gm::Line(as.character(f0_spn))
line_1 <- gm::Line(as.character(f1_spn))
m1 <- gm::Music() +
  gm::Meter(4, 4) +
  line_0 + line_1
gm::show(m1, to = c('score', 'audio'))

{width=95%}

4. Advanced installation

Python-based functions diarize and extract_features (when the latter is inferring f0_praat and fmt_praat features) require a configured Python environment.

4.1 Ubuntu

The following steps are used to fully configure voice on Ubuntu 24.04 LTS (Noble Numbat). Reports of inconsistencies are welcome.

4.1.1. Curl

Command line tool and library for transferring data with URLs.

# installing dependencies
sudo apt-get update
sudo apt-get install -y libssl-dev autoconf libtool make
# installing curl
sudo apt install curl
# verify installation
curl --version

4.1.2. ffmpeg

ffmpeg is a cross-platform solution to record, convert and stream audio and video.

sudo apt-get update
sudo apt-get install ffmpeg

4.1.3. Audio drivers and extra packages

sudo apt-get update
sudo apt-get install portaudio19-dev libasound2-dev libfontconfig1-dev libmagick++-dev libxml2-dev libharfbuzz-dev libfribidi-dev libgdal-dev cmake cmake-doc ninja-build

4.1.4. MuseScore

MuseScore is an open source notation software.

sudo add-apt-repository ppa:mscore-ubuntu/mscore-stable
sudo apt-get update
sudo apt-get install musescore

4.1.5. R

R is a free software environment for statistical computing and graphics. To find out your Ubuntu distribution use lsb_release -a at terminal.

sudo sh -c 'echo "deb https://cloud.r-project.org/bin/linux/ubuntu focal-cran40/" >> /etc/apt/sources.list.d/cran.list'
sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys E084DAB9 
sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 51716619E084DAB9
gpg -a --export E084DAB9 | sudo apt-key add -

sudo add-apt-repository ppa:c2d4u.team/c2d4u4.0+

sudo apt-get update && sudo apt-get upgrade
sudo apt-get install r-base r-base-dev

4.1.6. RStudio

RStudio is an Integrated Development Environment (IDE) for R. Check for updates here.

sudo apt-get update
sudo apt-get install gdebi-core
wget https://download1.rstudio.org/electron/jammy/amd64/rstudio-2025.05.0-496-amd64.deb
sudo gdebi rstudio-2025.05.0-496-amd64.deb

4.1.9. R packages

"Packages are the fundamental units of reproducible R code." Hadley Wickham and Jennifer Bryan. The installation may take several minutes. At terminal run:

sudo R

Running R as super user paste the following, row by row:

packs <- c('audio','reticulate','R.utils','seewave','tidyverse','tuneR','wrassp')
install.packages(packs, dep = TRUE)
update.packages(ask = FALSE)
devtools::install_github('egenn/music')
devtools::install_github('flujoo/gm')

To configure the gm package.

usethis::edit_r_environ()

Add the line MUSESCORE_PATH=/usr/bin/mscore to /root/.Renviron file. To exit use :wq at VI. Save and restart the R/RStudio session.

4.1.10. Miniconda

Miniconda is a free minimal installer for conda, an open source package, dependency and environment management system for any language—Python, R, Ruby, Lua, Scala, Java, JavaScript, C/ C++, FORTRAN and more, that runs on Windows, macOS and Linux.
Follow the instructions at https://docs.conda.io/en/latest/miniconda.html.

At terminal:

cd ~/Downloads/
wget -r -np -k https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
cd repo.anaconda.com/miniconda/
bash Miniconda3-latest-Linux-x86_64.sh

Do you accept the license terms? [yes|no] yes.

Miniconda3 will now be installed into this location: /home/user/miniconda3 [ENTER]

You can undo this by running conda init --reverse $SHELL? yes

Do you wish the installer to initialize Miniconda3 by running conda init? yes.

Close and reopen terminal.

conda update -n base -c defaults conda

The following packages will be INSTALLED/REMOVED/UPDATED/DOWNGRADED:... Proceed ([y]/n)? y

conda create -n pyvoice python=3.12

The following (NEW) packages will be downloaded/INSTALLED:... Proceed ([y]/n)? y

conda activate pyvoice
pip install -r https://raw.githubusercontent.com/filipezabala/voice/master/requirements.txt

4.2 MacOS

The following steps are used to fully configure voice on MacOS Sonoma (Link to MacOS Sequoia). Reports of inconsistencies are welcome.

4.2.1. Homebrew

Install Homebrew, 'The Missing Package Manager for macOS (or Linux)' and remember to brew doctor eventually. At terminal (command + space 'terminal') run:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

4.2.2. wget

GNU Wget is a free software package for retrieving files using HTTP, HTTPS, FTP and FTPS, the most widely used Internet protocols. It is a non-interactive commandline tool, so it may easily be called from scripts, cron jobs, terminals without X-Windows support, etc.

brew install wget

4.2.3. Python

Python is a programming language that integrate systems. According to this post, it is recommended to install Python 3.8 and 3.9 and make it consistent.

brew install python@3.12
python3 --version 
pip3 --version

4.2.4. ffmpeg

ffmpeg is a cross-platform solution to record, convert and stream audio and video. The installation may take several minutes.

brew install ffmpeg

4.2.5. XQuartz

The XQuartz project is an open-source effort to develop a version of the X.Org X Window System that runs on macOS.

• Download and run https://github.com/XQuartz/XQuartz/releases/download/XQuartz-2.8.5/XQuartz-2.8.5.pkg
• Will take around 320 MB of disk space
• Send XQuartz-2.8.5.dmg to Trash

4.2.6. MacPorts

Follow the instructions from https://guide.macports.org/chunked/installing.macports.html.

4.2.7. tcllib

sudo port selfupdate && sudo port upgrade tcllib
sudo port install tcllib

4.2.8. MuseScore

MuseScore is an open source notation software.

• Download and run https://musescore.org/en/download/musescore.dmg
• Drag MuseScore 4 to Applications folder
• Will take around 320 MB of disk space
• Unmount MuseScore-4.2.1 virtual disk and send MuseScore-4.2.1.240230937.dmg to Trash

4.2.9. R

R is a free software environment for statistical computing and graphics.

• Download and run the pkg file according to you architecture from https://www.r-project.org
• Will take around 180 MB of disk space

4.2.10. RStudio

RStudio is an Integrated Development Environment (IDE) for R.

• Download and run https://download1.rstudio.org/electron/macos/RStudio-2025.05.0-496.dmg
• Drag RStudio to Applications folder
• Will take around 770 MB of disk space
• Unmount RStudio virtual disk and send RStudio-2025.05.0-496.dmg to Trash
• Type command + space 'rstudio'
• Tools > Global Options... > Appearance > Merbivore (Restart required)

4.2.11. R packages

"Packages are the fundamental units of reproducible R code." Hadley Wickham and Jennifer Bryan. Type command + space 'terminal'

sudo R

Running R as super user paste the following, one line at a time.

packs <- c('audio','reticulate','R.utils','seewave','tidyverse','tuneR','wrassp')
install.packages(packs, dep = TRUE)
update.packages(ask = FALSE)
devtools::install_github('egenn/music')
devtools::install_github('flujoo/gm')

4.2.12. Miniconda

Miniconda is a free minimal installer for conda, an open source package, dependency and environment management system for any language—Python, R, Ruby, Lua, Scala, Java, JavaScript, C/ C++, FORTRAN and more, that runs on Windows, macOS and Linux.

For 64-bit version use

cd ~/Downloads
wget -r -np -k https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
cd repo.anaconda.com/miniconda/
bash Miniconda3-latest-MacOSX-x86_64.sh

For M1 version use

cd ~/Downloads
wget -r -np -k https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
cd repo.anaconda.com/miniconda/
bash Miniconda3-latest-MacOSX-arm64.sh

In order to continue the installation process, please review the license agreement. Please, press ENTER to continue ENTER.

You can undo this by running conda init --reverse $SHELL? yes

Close and reopen terminal.

export PATH="~/miniconda3/bin:$PATH"
conda update -n base -c defaults conda

The following packages will be INSTALLED/REMOVED/UPDATED/DOWNGRADED:... Proceed ([y]/n)? y

conda create -n pyvoice python=3.12

The following (NEW) packages will be downloaded/INSTALLED:... Proceed ([y]/n)? y

Close and reopen terminal.

conda activate base
conda activate pyvoice
pip install -r https://raw.githubusercontent.com/filipezabala/voice/master/requirements.txt

5. Diarize

# download
url0 <- 'https://github.com/filipezabala/voiceAudios/raw/main/wav/sherlock0.wav'
wavDir <- normalizePath(tempdir())
download.file(url0, paste0(wavDir, '/sherlock0.wav'), mode = 'wb')

Diarization can be performed to detect speaker segments (i.e., 'who spoke when').

# diarize
voice::diarize(fromWav = wavDir, toRttm = wavDir, token = 'YOUR_TOKEN')

The voice::diarize() function creates Rich Transcription Time Marked (RTTM)[^rttm] files, space-delimited text files containing one turn per line defined by NIST - National Institute of Standards and Technology. The RTTM files can be read using voice::read_rttm().

[^rttm]: See Appendix C at https://www.nist.gov/system/files/documents/itl/iad/mig/KWS15-evalplan-v05.pdf.

# read_rttm
(rttm <- voice::read_rttm(wavDir))

Finally, the audio waves can be automatically segmented.

# split audio wave
voice::splitw(fromWav = wavDir, fromRttm = wavDir, to = wavDir)
dir(wavDir, pattern = '.[Ww][Aa][Vv]$')

voice documentation built on Aug. 8, 2025, 6:41 p.m.