Tamar Lucassen's scientific contributions

Publications (3)

Preprint
We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide supervision, and are evaluated on how they impact speech recognition performance. We propose using keyword-dependent prec...
Preprint
Full-text available
This technical report describes our deep internationalization program for Gboard, the Google Keyboard. Today, Gboard supports 900+ language varieties across 70+ writing systems, and this report describes how and why we have been adding support for hundreds of language varieties from around the globe. Many languages of the world are increasingly use...

Citations

... One is to generate artificial audio for adaptation text instead of collecting real audio. Audio generation method could be based on multi-speaker neural text to speech (TTS) model [15][16][17][18][19] or spliced data method [20]. The neural transducer model could then be finetuned with artificial paired audio and text data. ...