Phoneme text with position suffix (e.g., "W_B" for word-beginning,
"AH1_I" for word-internal). The suffix indicates the phone's position
within the word: _B (beginning), _I (internal), _E (end), _S (singleton).
Goodness of Pronunciation (GoP) score ranging from 0 to 1. Higher values indicate better pronunciation match.
Start time of this phone in seconds from the beginning of the audio.
Duration of this phone in seconds.
Phone-level recognition result with timing and optional pronunciation scoring.
Phone-level details (text, timing) are always available on each ASRWord. The
pronunciationScorefield is only populated when Goodness of Pronunciation (GoP) scoring is enabled by passingcomputeGoP: trueto prepareForListening.