This is most probably a/an ______: We can use automatic audio processing algorithms to robustly detect speech in the audio, and then split speech into short, easy to transcribe segments. We load sequences of speech segments into a specially designed transcription interface. On the interface a human transcriber doesn’t need to find and segment speech manually, or explicitly control audio playback. The transcriber only needs to listen and type. Playback stays synchronized to the transcriber’s speed of transcription