As another example, in some embodiments, the first speech recognition system 134 and the second speech recognition system 136 may share hardware, software, or other components. In these and other embodiments, the first speech recognition system 134 and the second speech recognition system 136 may not be completely separate systems. Rather, reference to the first speech recognition system 134 and the second speech recognition system 136 may refer to a manner in how the transcriptions are generated more than separate systems. As another example, in some embodiments, the components of the transcription system 130 may be coupled over a network. For example, the first speech recognition system 134 may be coupled with second speech recognition system 136 over a network, such as the network 102. Additionally or alternatively, the first speech recognition system 134 and/or the second speech recognition system 136 may be part of third-party systems that may be used by the transcription system 130 to obtain the transcriptions. Further, in some embodiments, the transcription system 120 may utilize or include any number of speech recognition systems in addition to or instead of the first speech recognition system 134 and/or the second speech recognition system 136.

Further, the locations of certain operations being described as being performed are given as examples and not limiting. For example, in some embodiments, the first device 104 and/or the second device 106 may be configured to perform one or more operations related to selection of a transcription generation technique.