In some embodiments, the first speech recognition system 134 and the second speech recognition system 136 may be similar speech recognition systems. For example, in some embodiments, the first speech recognition system 134 and the second speech recognition system 136 may both be automatic systems that automatically recognize speech independent of human interaction to generate the transcription. In these and other embodiments, the first speech recognition system 134 and the second speech recognition system 136 may include speech engines that are trained to recognize speech. The speech engines may be trained for general speech and not specifically trained using speech patterns of the participants in the communication session, e.g., the first user 110 or the second user 112. Alternatively or additionally, the speech engines may be specifically trained using speech patterns of one of the participants of the communication session. Alternatively or additionally, both of the first speech recognition system 134 and the second speech recognition system 136 may be re-voicing systems.

In some embodiments, the first speech recognition system 134 and the second speech recognition system 136 may be different speech recognition systems. For example, in some embodiments, one of the first speech recognition system 134 and the second speech recognition system 136 may be an automatic system and another may be a re-voicing system. Additionally or alternatively, the first speech recognition system 134 may be a first automatic system and the second speech recognition system 136 may be a second automatic system that may use a different ASR algorithm or engine than the first automatic system.