LJ Speech - Aligned IPA transcriptions

Files:

• grids.zip

  • contains TextGrids for all audio files containing three tiers words, phonemes and transcription
    • words contains the aligned normalized English words
    • phonemes contains IPA pronunciations transcribed using CMU dictionary which then were aligned with Montreal Forced Aligner. The pronunciations were then mapped from ARPAbet to IPA and duration marks were applied (without punctuation)
    • transcription contains unaligned phonemes including punctuation and word boundary labels (SIL0)

• preview.png

  • preview of the first TextGrid opened in Praat

• words-vocabulary.txt

  • contains all words from tier words

• phonemes-vocabulary.txt

  • contains all phonemes from tier phonemes

• transcription-vocabulary.txt

  • contains all phonemes/punctuation from tier transcription

• phonemes-durations.pdf

  • contains the plotted phoneme duration distribution of tier phonemes

• phonemes-durations-simple.pdf

  • contains the plotted phoneme duration distribution of tier phonemes if all duration markers are ignored

• pronunciations.dict

  • contains the pronunciations for each word including punctuation and weights (occurrence)

• script.sh

  • contains the script to reproduce all results

Phoneme duration marker:

• ˘ -> [0, 20) percentile
• ˑ -> [80, 90) percentile
• ː -> [90, inf) percentile

Silence marker:

• SIL0 -> no silence
• SIL1 -> [0, 33.33) percentile
• SIL2 -> [33.33, 66.66) percentile
• SIL3 -> [66.66, inf) percentile