1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

00:18:28

0 views

We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also

Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

00:00:00

0 views

We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also