About
Forced alignment technology
Forced alignment (FA) refers to the automatic process by which speech recordings are phonetically time-stamped with the help of Hidden Markov models or Deep Neural Networks. Autophon uses the latter by means of the The Montreal Forced Aligner. The software outputs a time-stamped phonetic annotation that is readable in Praat, based on an optimization of two user inputs: (1) the speech recording and (2) a corresponding orthographic transcription. For an FA tool to work for a particular language, an acoustic model must be trained and an accompanying pronunciation lexicon must be built that covers every word in the language. FA is useful because it automates an otherwise resource-intensive task A phonetic annotation done by hand can take between 250 and 400 minutes per recorded minute. In a place like Scandinavia where labor costs are high, this has presented a barrier for linguists.
A free online tool
The app is free of charge and was built so that students and researchers could access forced-alignment tools efficiently and without the need for command-line programs.
Data security
Everything you upload is encrypted and sent to a server in Frankfurt, Germany, that is run by Digital Ocean (server FRA1). To increase security and reduce the chance of a data breach, sound files are also immediately deleted after alignment. On the other hand, finished TextGrids are stored in your account for as long as you like. Once, however, you delete them, they will also be removed from our server permanently.
Platform stability
Autophon is in beta, which means it is still working through some bugs. Contact us if you encounter any issues or have any feedback.
Register to start using!
Video demo
Accuracy
Accuracy metrics are only available for a few high-resource languages. These can be accessed in the user guides below. Reach out to Support if you have any manually-aligned files that you are willing to share with us for the purposes of validating a language model.
User Guides
Ownership
Autophon was founded and is managed by Nate Young and run by the essential stakeholders listed on our Team page. Initially started with private means, it has now grown in scope with a grant from the Swedish Academy, a grant from the Department of Linguistics and Scandinavian Studies at The University of Oslo, and has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 892963.