Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi

@inproceedings{McAuliffe2017MontrealFA,
  title={Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi},
  author={Michael McAuliffe and Michaela Socolof and Sarah Mihuc and M. Wagner and Morgan Sonderegger},
  booktitle={INTERSPEECH},
  year={2017}
}
We present the Montreal Forced Aligner (MFA), a new opensource system for speech-text alignment. [...] Key Method MFA uses Kaldi instead of HTK, allowing MFA to be distributed as a stand-alone package, and to exploit parallel processing for computationally-intensive training and scaling to larger datasets. We evaluate MFA’s performance on aligning word and phone boundaries in English conversational and laboratory speech, relative to human-annotated boundaries, focusing on the effects of aligner architecture and…Expand
172 Citations
MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation
  • 1
  • PDF
Developing Resources for Automated Speech Processing of Quebec French
  • Highly Influenced
  • PDF
Joint Phoneme Alignment and Text-Informed Speech Separation on Highly Corrupted Speech
  • 2
  • Highly Influenced
  • PDF
Phoneme Boundary Detection Using Learnable Segmental Features
  • 4
  • PDF
Evaluating and Optimizing Prosodic Alignment for Automatic Dubbing
  • PDF
Learning to Count Words in Fluent Speech Enables Online Speech Recognition
  • 2
  • PDF
FT Speech: Danish Parliament Speech Corpus
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 29 REFERENCES
Prosodylab-aligner: A tool for forced alignment of laboratory speech
  • 133
  • Highly Influential
  • PDF
Using automatic alignment to analyze endangered language data: testing the viability of untrained alignment.
  • 27
  • PDF
EasyAlign: An Automatic Phonetic Alignment Tool Under Praat
  • 236
  • PDF
A grapheme-based method for automatic alignment of speech and text data
  • 32
  • PDF
SPPAS: a tool for the phonetic segmentation of speech
  • 61
  • PDF
Librispeech: An ASR corpus based on public domain audio books
  • 1,570
  • PDF
GlobalPhone: A multilingual text & speech database in 20 languages
  • 96
  • PDF
...
1
2
3
...