PROPER NOUN RECOGNITION IN END-TO-END SPEECH RECOGNITION

PROPER NOUN RECOGNITION IN END-TO-END SPEECH RECOGNITION

A method (400) for training a speech recognition model (200) with a minimum word error rate loss function includes receiving a training example (302) including a proper noun and generating a plurality of hypotheses (222) corresponding to the training example. Each hypothesis of the plurality of hypo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: PUNDAK, Golan, SAINATH, Tara, N, PEYSER, Charles, Caleb
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method (400) for training a speech recognition model (200) with a minimum word error rate loss function includes receiving a training example (302) including a proper noun and generating a plurality of hypotheses (222) corresponding to the training example. Each hypothesis of the plurality of hypotheses represents the proper noun and includes a corresponding probability that indicates a likelihood that the hypothesis represents the proper noun. The method also includes determining that the corresponding probability associated with one of the plurality of hypotheses satisfies a penalty criteria. The penalty criteria indicating that the corresponding probability satisfies a probability threshold, and the associated hypothesis incorrectly represents the proper noun. The method also includes applying a penalty (332) to the minimum word error rate loss function.