Doublets or multiplets are earthquakes with nearly identical waveforms. First observed on volcanoes, doublets are found in tectonic environments. Doublets can be relocated relatively with a precision of a few meters. Very good doublets separated by a large time lapse are essential for detecting slow temporal variations of crustal properties. We present basic techniques for selecting and processing doublets. In a seismic database, coherency between all pairs of seismograms is computed and high coherency pairs are candidate doublets. Time delays between waveforms are measured by cross-correlation techniques; a precision of 1 ms is common for good pairs sampled at 100 Hz. Several techniques can relocate one event relatively to the other and P and S delay residuals are obtained. Clock precision remains critical when searching for a few millisecond anomalies. Delays in the coda are analyzed by a cross-spectral moving window (CSMW) or a cross-correlation moving window (CCMW) analysis. Time delay measured in the coda shows variations even when the time elapsed between the two events of a doublet is extremely short. These variations are due to hypocenter separation and to changes in the waves which form the early coda. When seismic velocity is changing homogeneously in the propagation medium, the delay of the coda is proportional to lapse time. Thus, the slope α of the delay in the coda is a very precise (up to 10−4) measurement of the change in S-wave velocity ΔVS/VS, α = −ΔVS/VS. Relative changes of delay on the horizontal components can detect temporal variations in S-wave splitting and anisotropy. Temporal changes in coda Q may be reflected in the coda amplitude ratio measured in several frequency bands. However, minor changes in sources induce variations in early coda (the coda that just follows the S wave) amplitude ratios, comparable to those due to attenuation changes. Therefore, the interpretation of coda amplitude ratios in terms of coda Q changes should be undertaken in the late coda only, using a statistical approach. Good doublets are seldom, so we present a technique that creates “virtual doublets” from the correlation of seismic noise long sequences. Temporal variations of physical properties in surface layers are recovered by a CCMW analysis of these “virtual doublets.” This is an interesting method for measuring strain variations preceding volcanic eruptions. Many other applications should blossom in the near future. At last, we present teleseismic doublets which are a tool for measuring the rate of rotation of the inner core of the Earth. The goal of this chapter is to show that doublet processing is elementary but that the detection of temporal variations of velocity or attenuation remains quite difficult. Excellent doublets should be selected to study temporal variations and such very good natural doublets are few in most seismic regions.