Difference between revisions of "2019:Automatic Lyrics-to-Audio Alignment"

From MIREX Wiki
(Added Jamendo dataset)
Line 47: Line 47:
 
You can read in detail about how the dataset was used for the first time here: [https://pdfs.semanticscholar.org/547d/7a5d105380562ca3543bf05b4d5f7a8bee66.pdf Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment]. The dataset has been kindly provided by Sungkyun Chang.
 
You can read in detail about how the dataset was used for the first time here: [https://pdfs.semanticscholar.org/547d/7a5d105380562ca3543bf05b4d5f7a8bee66.pdf Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment]. The dataset has been kindly provided by Sungkyun Chang.
  
* file duration up to 5:40 minutes (total time: 1:19:12 hours)
+
* file duration up to 5:40 minutes (total time: 1h 19m)
 
* 5050 words annotated in total
 
* 5050 words annotated in total
 
  
 
==== Gracenote Dataset ====
 
==== Gracenote Dataset ====
 
The dataset contains 15 pop music song excerpts in English with annotations of beginning-timestamps of each word. 8 song excerpts have instrumental accompaniment. The other 7 song excerpts have has two versions: with instrumental accompaniment and a cappella singing.
 
The dataset contains 15 pop music song excerpts in English with annotations of beginning-timestamps of each word. 8 song excerpts have instrumental accompaniment. The other 7 song excerpts have has two versions: with instrumental accompaniment and a cappella singing.
  
* file duration up to 1:11 (total time: 11:42 minutes)
+
* file duration up to 1:11 (total time: 11m)
 
* 1181 words annotated in total
 
* 1181 words annotated in total
 +
 +
==== Jamendo Dataset ====
 +
This dataset contains 20 full-duration music pieces with 10 different Western music genres, annotated with start-of-word timestamps. All songs have instrumental accompaniment. For more information refer to the [http://www.github.com/f90/jamendolyrics dataset homepage] and the [https://arxiv.org/abs/1902.06797 paper].
 +
 +
* file duration up to 4:43 (total time: 1h 12m)
 +
* 5677 words annotated in total
  
 
=== Phonetization ===
 
=== Phonetization ===
Line 66: Line 71:
 
* CD-quality (PCM, 16-bit, 44100 Hz)
 
* CD-quality (PCM, 16-bit, 44100 Hz)
 
* single channel (mono) for a cappella and two channels for original
 
* single channel (mono) for a cappella and two channels for original
 
  
 
==Evaluation==
 
==Evaluation==

Revision as of 13:01, 5 July 2019

Description

The task of automatic lyrics-to-audio alignment has as an end goal the synchronization between an audio recording of singing and its corresponding written lyrics. The beginning timestamps of lyrics units can be estimated on different granularity: phonemes, words, lyrics lines, phrases. For this task word-level alignment is required.

  -----------------------    ---------------------------------------------------
  | Mixed singing audio |    | Lyrics at word-level: no more carefree ... ... |
  -----------------------    ---------------------------------------------------
                 |                                            |
                  --------------------------------------------
                                     |
                             --------------------
                             | Alignment system |
                             --------------------
                                     |
                                     |
                             --------------------------
                             | 0.123 	0.798  no     |
                             | 0.798 	1.123  more   |
                             | 1.345 	2.176  carefree|
                             | ... ...                |
                             --------------------------

The algorithm receives two inputs - mixed singing audio (singing voice + musical accompaniment) and its corresponding lyrics at word-level, outputs the onset and offset timestamps (second) of each word.

Datasets

Training Dataset

The DAMP dataset contains a large number (34 000+) of a cappella recordings from a wide variety of amateur singers, collected with the Sing! Karaoke mobile app in different recording conditions, but generally with good audio quality. A carefully curated subset DAMPB of 20 performances of each of the 300 songs has been created by (Kruspe, 2016). Here is the list of recordings.

Evaluation Datasets

Hansen's Dataset

The dataset contains 9 pop music songs in English with annotations of both beginnings- and ending-timestamps of each word. The ending timestamps are for convenience (copies of next word's beginning timestamp) and are not used in the evaluation. Sentence-level annotations are also provided. The audio has two versions: the original with instrumental accompaniment and a cappella singing voice only one. An example song can be seen here

You can read in detail about how the dataset was made here: Recognition of Phonemes in A-cappella Recordings using Temporal Patterns and Mel Frequency Cepstral Coefficients. The dataset has been kindly provided by Jens Kofod Hansen.

  • file duration up to 4:40 minutes (total time: 35:33 minutes)
  • 3590 words annotated in total

Mauch's Dataset

The dataset contains 20 pop music songs in English with annotations of beginning-timestamps of each word. Non-vocal sections are not explicitly annotated (but remain included in the last preceding word). We prefer to leave it this way, to enable comparison to previous work, evaluated on this dataset. The audio has instrumental accompaniment. An example song can be seen here.

You can read in detail about how the dataset was used for the first time here: Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment. The dataset has been kindly provided by Sungkyun Chang.

  • file duration up to 5:40 minutes (total time: 1h 19m)
  • 5050 words annotated in total

Gracenote Dataset

The dataset contains 15 pop music song excerpts in English with annotations of beginning-timestamps of each word. 8 song excerpts have instrumental accompaniment. The other 7 song excerpts have has two versions: with instrumental accompaniment and a cappella singing.

  • file duration up to 1:11 (total time: 11m)
  • 1181 words annotated in total

Jamendo Dataset

This dataset contains 20 full-duration music pieces with 10 different Western music genres, annotated with start-of-word timestamps. All songs have instrumental accompaniment. For more information refer to the dataset homepage and the paper.

  • file duration up to 4:43 (total time: 1h 12m)
  • 5677 words annotated in total

Phonetization

A popular choice for phonetization of the words is the CMU pronunciation dictionary. One can phonetize them with the online tool. A list of all words of both datasets, which are outside of the list of CMU words is given here.

Audio Format

The data are sound wav/mp3 files, plus the associated word boundaries (in csv-like .txt/.tsv files)

  • CD-quality (PCM, 16-bit, 44100 Hz)
  • single channel (mono) for a cappella and two channels for original

Evaluation

The submitted algorithms for both subtasks will be evaluated at the word boundaries for the original mixed songs (a cappella singing + instrumental accompaniment). Evaluation metrics only on the a cappella singing will be reported as well, for the sake of getting insights on the impact of instrumental accompaniment on the algorithm, but will not be considered for the ranking.

Average absolute error/deviation Initially utilized in Mesaros and Virtanen (2008), the absolute error measures the time displacement between the actual timestamp and its estimate at the beginning and the end of each lyrical unit. The error is then averaged over all individual errors. An error in absolute terms has the drawback that the perception of an error with the same duration can be different depending on the tempo of the song. Here is a test of using this metric.

Percentage of correct segments The perceptual dependence on tempo is mitigated by measuring the percentage of the total length of the segments, labeled correctly to the total duration of the song. This metric is suggested by Fujihara et al. (2011), Figure 9. Here is a test of using this metric.

Percentage of correct estimates according to a tolerance window A metric that takes into consideration that the onset displacements from ground truth below a certain threshold could be tolerated by human listeners. We use 0.3 seconds as the tolerance window. This metric is suggested in Integrating Additional Chord Information Into HMM-Based Lyrics-to-Audio Alignment. Here is a test of using this metric.

For more detailed definition and formulas about the metrics, please check the section 2.2.1 of this thesis.

To obtain all three metrics for one detected output:

python eval.py <file path of the reference word boundaries> <file path of the detected word boundaries>

Note that evaluation scripts depend on mir_eval.


Submission Format

Submissions should be packaged and contain at least two files: The algorithm itself (as a binary or source code) and a README containing contact information and detailing, in full, the use of the algorithm.

Input Data

Participating algorithms will have to receive the following input format:

  • Audio in wav, 44.1kHz, subtask1: mono, subtask2: stereo.
  • Lyrics in .txt file where each word is separated by a space, each lyrics phrase is separated by a line break mark (\n).

Output File Format

The alignment output file format is a tab-delimited ASCII text format.

Three column text file of the format

<onset_time(sec)>\t<offset_time(sec)>\t<label>\n
<onset_time(sec)>\t<offset_time(sec)>\t<label>\n
...

where \t denotes a tab, \n denotes the end of the line. The < and > characters are not included. An example output file would look something like:

0.000    5.223    label1
5.223    15.101   label2
15.101   20.334   label3

where label is Mandarin syllable pinyin for subtask 1 and English word for subtask 2.

NOTE: the offset timestamps column is utilized only by the percentage of correct segments metric. Therefore skipping the second column is acceptable, and could result in degraded performance of this respective metric only.

Command line calling format

The submitted algorithm must take as arguments .wav file, .txt file as well as the full output path and filename of the output file. The ability to specify the output path and file name is essential. Denoting the input .wav file path and name as %input_audio; the lyrics .txt file as %input_txt and the output file path and name as %output, a program called foobar could be called from the command-line as follows:

foobar %input_audio %input_txt %output
foobar -i %input_audio -it %input_txt  -o %output


README File

A README file accompanying each submission should contain explicit instructions on which subtask to participate and how to run the program (as well as contact information, etc.). In particular, each command line to run should be specified, using %input for the input sound file and %output for the resulting text file.

Submission closing dates

Closing date: TBD (end of September 2019)

Question?

  • send us an email - d.stoller@qmul.ac.uk (Daniel Stoller ) or info@voicemagix.com (Georgi Dzhambazov)

Potential Participants