-
Loading metrics
Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit
-
Denis Arnold ,
* E-mail: denis.arnold@uni-tuebingen.de, arnold@ids-mannheim.de
Affiliations Quantitative Linguistics, Seminar für Sprachwissenschaft, Eberhard Karls Universität Tübingen, Tübingen, Germany, Institut für Deutsche Sprache, Mannheim, Germany
⨯ - Fabian Tomaschek,
- Konstantin Sering,
- Florence Lopez,
- R. Harald Baayen
http://orcid.org/0000-0003-0540-3872
Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit
- Denis Arnold,
- Fabian Tomaschek,
- Konstantin Sering,
- Florence Lopez,
- R. Harald Baayen
x
- Published: April 10, 2017
- https://doi.org/10.1371/journal.pone.0174623