Catching the Lyrics: Intelligibility in Twelve Song Genres

  title={Catching the Lyrics: Intelligibility in Twelve Song Genres},
  author={Nathaniel Condit-Schultz and David Huron},
  journal={Music Perception: An Interdisciplinary Journal},
Although purely instrumental music is commonplace, much of the world’s most popular music is sung with lyrics. However, it is evident that listeners don’t always attend to lyrics and that those who do aren’t always successful in deciphering them. An empirical study is reported whose goal is to measure the intelligibility of lyrics in commercial recordings of music from a variety of genres. Thirty participants were exposed to 120 brief musical excerpts from twelve song genres: Avante-garde… 

Figures and Tables from this paper

Intelligibility of Sung Lyrics: A Pilot Study
A system to automatically assess the intelligibility of sung lyrics and achieves 66% accuracy for 3 classes of intelligibility, particularly interested in being able to identify songs which are intelligible to second language learners.
Singing and Accompaniment Support the Processing of Song Lyrics and Change the Lyrics' Meaning
A growing body of evidence indicates that music can support the processing of language. Some of its beneficial effects may even occur after one exposure. Accompaniment can also have an impact: in
Making myself understood: perceived factors affecting the intelligibility of sung text
Empirical research is needed to explore some of the factors believed to have most impact on intelligibility in sung text intelligibility, and has the potential to inform pedagogy for singers, composers, and choral directors.
Word Intelligibility in Multi-voice Singing: The Influence of Chorus Size.
Data Science Approach to Compare the Lyrics of Popular Music Artists
Popular music lyrics exhibit clear differences between songwriters. This study describes a quantitative approach to the analysis of popular music lyrics. The method uses explainable measurements of
Vowel Formant Structure Predicts Metric Position in Hip-hop Lyrics
In order to be heard over the low-frequency energy of a loud orchestra, opera singers adjust their vocal tracts to increase high-frequency energy around 3,000 Hz (known as a “singer's formant”). In
Music-robust Automatic Lyrics Transcription of Polyphonic Music
It is shown that music-robust features specially improve the lyrics transcription performance in metal genre of songs, where the background music is loud and dominant, and language model interpolation between a general-purpose language model and an in-domain lyrics-specific language model provides further improvement in transcription results.
Automatic Lyrics Transcription in Polyphonic Music: Does Background Music Help?
This work proposes to learn music genre-specific characteristics to train polyphonic acoustic models, and explicitly model the characteristics of music, instead of trying to remove the background music as noise.
Detection of pitch errors in well-known songs
We examined pitch-error detection in well-known songs sung with or without meaningful lyrics. In Experiment 1, adults heard the initial phrase of familiar songs sung with lyrics or repeating
Genre-conditioned Acoustic Models for Automatic Lyrics Transcription of Polyphonic Music
This work proposes to transcribe the lyrics of polyphonic music using a novel genre-conditioned network that adopts pre-trained model parameters, and incorporates the genre adapters between layers to capture different genre peculiarities for lyrics-genre pairs, thereby only requiring lightweight genre-specific parameters for training.


Music and Lyrics Interactions and their Influence on Recognition of Sung Words: An Investigation of Word Frequency, Rhyme, Metric Stress, Vocal Timbre, Melisma, and Repetition Priming
This study investigated several factors presumed to influence the intelligibility of song lyrics. Twenty-seven participants listened to recordings of musical passages sung in English; each passage
Perceptual confusions of high-pitched sung vowels.
Comparison of Word Intelligibility in Spoken and Sung Phrases
Twenty listeners were exposed to spoken and sung passages in English produced by three trained vocalists. Passages included representative words extracted from a large database of vocal lyrics,
Increasing the intelligibility of sung vowels.
Investigation of the intelligibility of the front vowels as sung in four different ways indicates that increased intelligibility across conditions is a function of increased energy in the higher harmonics and presence of consonantal transitions.
The magical number seven plus or minus two: some limits on our capacity for processing information.
The theory provides us with a yardstick for calibrating the authors' stimulus materials and for measuring the performance of their subjects, and the concepts and measures provided by the theory provide a quantitative way of getting at some of these questions.
Chunk limits and length limits in immediate recall: a reconciliation.
  • Zhijian Chen, N. Cowan
  • Psychology
    Journal of experimental psychology. Learning, memory, and cognition
  • 2005
The authors investigated this question by teaching new paired associations between words to create 2-word chunks, and results suggest that both chunk capacity limits and length limits come into play.
The development and cross-validation of a self-report inventory to assess pure-tone threshold hearing sensitivity.
A self-report inventory suitable for group testing or survey administration, which appears to have high correlation with pure-tone hearing thresholds, and a conversion equation with estimated variability is provided for point estimates of pure- tone hearing thresholds from the HSI scores.
Working memory capacity for spoken sentences decreases with adult ageing: Recall of fewer but not smaller chunks in older adults
An age-related decline in working memory capacity measured in chunks appears to account for deficits in memory for spoken language.
The effect of pitch‐related changes on the perception of sung vowels
Vowel discrimination and perception were studied for a soprano singing on a fundamental frequency between 262 and 1047 Hz. The vowels were identified by 28 listeners as 1 of 12 American English
Functional-relationships of language and music — The 2-profile view of text
  • disposition. Linguistique,
  • 1992