Despite infants’ immature resolution of pitch and timing, they are surprisingly proficient at holistic processing of pitch and timing patterns. Like adults, they recognize the invariance of melodies across pitch levels and the invariance of rhythmic patterns across tempos. They also exhibit long-term memory for melodies, and their memory is especially detailed and enduring for vocal melodies. In some respects, they are more flexible music listeners and learners than their adult counterparts. Although adults’ musical engagement is commonly unimodal and solitary, infants typically experience music multimodally in dyadic contexts (e.g., Western caregivers sing lively play songs in face-to-face contexts; non-Western caregivers sing soothing lullabies to carried infants). Such singing is more effective than infant-directed speech in regulating infant arousal and affect. Moreover, caregivers’ songs have social as well as emotional significance for infants, influencing their behavior toward unfamiliar individuals who sing such songs.