Semantic Scholar Open Access 1990 559 sitasi

Speech recognition

Steffen Schneider Alexei Baevski R. Collobert Michael Auli

Lihat Sumber DOI

Abstrak

Currently, the research group has investigated deep neural network-based acoustic modeling technologies within the framework of the "Telemedicine" TÁMOP-4.2.2.A project. The group's researchers were among the first who analyzed the applicability of rectifier deep neural networks in speech recognition, and they obtained a new record of recognition accuracy on the widely studied TIMIT database using a special neural network that has a convolutional architecture. The various types of deep neural network algorithms were also evaluated and compared on Hungarian speech recognition tasks. The team's researchers won the "Emotion Sub-Challenge" of the "Computational Paralinguistic Challenge" of the Interspeech conference by making use of the AdaBoost algorithm.

Topik & Kata Kunci

Computer Science

Penulis (4)

Steffen Schneider

Alexei Baevski

R. Collobert

Michael Auli

Format Sitasi

APA MLA BibTeX

Schneider, S., Baevski, A., Collobert, R., Auli, M. (1990). Speech recognition. https://doi.org/10.1002/j.2637-496X.1990.tb05934.x

Akses Cepat

Lihat di Sumber doi.org/10.1002/j.2637-496X.1990.tb05934.x

Informasi Jurnal

Tahun Terbit: 1990
Bahasa: en
Total Sitasi: 559×
Sumber Database: Semantic Scholar
DOI: 10.1002/j.2637-496X.1990.tb05934.x
Akses: Open Access ✓