Download | - View final version: AlloVera: a multilingual allophone database (PDF, 380 KiB)
|
---|
Author | Search for: Mortensen, David R.; Search for: Li, Xinjian; Search for: Littell, Patrick1; Search for: Michaud, Alexis; Search for: Rijhwani, Shruti; Search for: Anastasopoulos, Antonios; Search for: Black, Alan W.; Search for: Metze, Florian; Search for: Neubig, Graham |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Format | Text, Article |
---|
Conference | 12th Language Resources and Evaluation Conference (LREC 2020), May 11-16, 2020, Marseille, France [Held Virtually] |
---|
Subject | phonology; allophones; database; automatic speech recognition |
---|
Abstract | We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a “universal” allophone model, Allosaurus, built with AlloVera, outperforms “universal” phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology. |
---|
Publication date | 2020-05-16 |
---|
Publisher | European Language Resources Association |
---|
Licence | |
---|
Related data | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 2e329f58-1437-40f2-bfe0-6b64401c4553 |
---|
Record created | 2021-06-21 |
---|
Record modified | 2021-06-21 |
---|