Sperm-whale codas are usually described by the number and timing of their clicks. Earlier acoustic studies showed that individual clicks and longer coda sequences contain additional organization. We ask how that organization compares with music, whose smaller sounds also form larger units and ordered sequences. We compare codas with performed violin music, drum grooves, and sung melodies. Their sequences resemble music in some measures of predictability, yet codas show a different relationship between the smaller sounds within a unit and the order of units across a sequence. This combination was not observed in the musical references tested. Coda timing also varies coherently and carries information about individual callers. The recordings show another striking property: broad, reproducible variation along acoustic dimensions associated with human ratings of emotion, with a range comparable to human audio in most eligible tests. These findings motivate an acoustic blueprint that describes natural codas beyond their click timing. Its importance is apparent in synthetic audio: WhAM produces recognizable coda-like recordings, yet the tested clips remain distinguishable from natural codas in five of six acoustic comparisons after strict matching. The blueprint provides a fuller way to study natural codas and to evaluate how faithfully synthetic recordings represent them.
Figures & tables
Figure 1: Example codas and musical recordings used in the comparison, shown as waveforms and spectrograms. Each excerpt retains its original duration.
Question
What we measure
Main comparison or control
How do coda sequences compare with music?
Repetition, choices of next sounds, and prediction from earlier sounds
Unseen recording sources; matched event counts and frequencies; repetition-aware prediction
Do smaller sounds organize each unit similarly?
Contribution of constituent types and their original order to whole-unit acoustic form
Timing-only prediction; rearrangements retaining the same sounds and onset positions
What information is carried by click timing?
Coordinated changes in intervals and prediction of caller identity
Shuffled timing; unseen dates; recording-metadata and label controls
How much emotion-relevant variation occurs?
Reproducibility and range along human-rated valence and arousal directions
Validation on held-out human audio; resampling by recording source; measured-acoustic adjustment
Do selected properties respond to alteration?
Changes in sequence and waveform measurements following order or timing edits
Randomized changes and controls for edit severity
Do synthetic codas reproduce natural acoustics?
Natural–synthetic difference across six acoustic descriptions
Independent natural reference sets and strict matching of measured recording properties
Table 1: Main measurements and controls used in this study.
Figure 2: How constituent composition, original ordering, and earlier sequence context contribute in codas and the three structured musical references. Asterisks mark Holm-corrected ordering or prediction results; full estimates and controls appear in the Supplement.
Finding
Result
Reference or control
Adjacent click intervals change together
Correlation 0.13
Shuffled reference near −0.12 ; adjusted p=0.0015
Phrase-final timing shift
p=0.061
Not supported after correction
Caller recognition from repertoire and rhythm
Balanced accuracy 0.43
Shuffled labels 0.12 ; p=0.0012
Caller information beyond recording context
Accuracy gain +0.19
95% interval [0.05,0.31]
Caller recognition from fine timing
Balanced accuracy 0.36
p=0.0008
Human-validated reference directions
23 of 24 eligible
One excluded from confirmatory tests
Table 2: Main timing, caller, and emotion-reference results.
Figure 3: Strictly matched natural–WhAM acoustic comparison. Points show residual MMD 2 gaps relative to an independent natural–natural reference; bars show 95% intervals. Five of six intervals lie above zero. The comparison uses 17 generated codas within joint measured-nuisance support and two independent weighted natural donor panels.
Sperm-whale codas are usually described by the number and timing of their clicks. These measures have revealed patterns in whale communication, but leave open how click sound contributes beyond timing and whether the order of whole codas carries additional structure. We investigate these questions through two tiers of acoustic organization, first within codas and then across coda sequences. Frozen pretrained audio encoders provide a framework for measuring acoustic variation beyond timing. We use them to identify recurring forms independently for clicks and whole codas in 1,483 codas, then validate their differences through direct waveform measurements. Within codas, click sound provides information beyond timing alone, while timing remains informative when click composition is held fixed. At the level of complete codas, we also find recurring acoustic forms whose differences are not fully captured by conventional timing-based types. With these forms identified, we examine how ordering contributes at each tier. Within codas, click-form order adds little predictive information beyond composition. Across codas, knowing the last two codas improves prediction over knowing only the last one. Together, these findings support two tiers with different organizing rules: acoustic composition and rhythmic timing within codas, and predictive relationships among whole codas across recorded sequences.
Mudit Sinha, Sanika Chavan
Independent Researcher, San Bruno, California 94066, United States
Comparing acoustic structure across very different vocal corpora is difficult because the recordings use different native event units, contain different amounts of sequence, and were collected under different conditions. We develop a matched procedure for comparing such corpora without forcing them into the same event definition. Frozen audio encoders provide a common acoustic representation for recorded events, while matched sampling gives each corpus the same amount of evidence for acoustic and sequence analysis. We apply this procedure to sperm-whale codas, human speech phones, Bengalese-finch syllables, and common-marmoset calls. The comparison reveals different patterns across the four corpora. Sperm-whale recordings stand out broadly: new acoustic forms continue to appear, while their sequences also show strong organization and repetition. Finch recordings show the strongest organization of sounds over time, especially in how neighboring sounds and repeated patterns are arranged. Direct temporal and spectral measurements show that these differences are also present in the recorded sounds themselves. The comparison provides a practical way to measure acoustic diversity and temporal organization across very different vocal corpora by combining a common acoustic representation with matched observation opportunity, without treating their native sounds as equivalent.
Mudit Sinha, Sanika Chavan
Independent Researcher, San Bruno, California 94066, United States
Sperm whales (Physeter macrocephalus) communicate through short click sequences called codas, whose structure includes the rhythmic pattern of inter-click intervals (ICI) and the spectral composition of the clicks. In this paper, we propose the Dual-Channel Contrastive Encoder (DCCE), which explicitly encodes rhythm and spectral information with separate encoders before fusing them. We evaluate DCCE on three coda-understanding tasks: social unit, coda type, and individual identification. We compare DCCE against strong baselines from literature under a common linear-probe protocol and analyze the role of each channel and training objective through ablations. On 1,383 codas, shared partitions and validation-only layer selection support three random splits and three recording-date-disjoint folds. DCCE with unit pairing and type supervision achieves mean random-split macro-F1 of 0.901/0.865/0.597 for unit/type/identity. Raw ICI remains strongest for type (0.987), and ICI plus temporal mel statistics is a strong identity reference (0.724). An auxiliary identity objective improves spectral-branch identity prediction but does not improve the mean fused-identity score in this configuration. Date-grouped evaluation and four year holdouts expose generalization limits. The results support task-dependent combinations of timing and spectral information, without establishing independent biological channels or general architectural superiority. Code, notebooks, and complete results are available at https://dcce-research-site.vercel.app.
João Victor Quintanilha, Emma Virnelli, Shuo Zhang