Collection:
In this work, an effective data scheduling strategy for semi- supervised learning (SSL) for acoustic modeling in automatic speech recognition is explored. The conventional approach uses a seed model trained with supervised data to automatically recognize
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Videos in this product
Incremental Semi-Supervised Learning For Multi-Genre Speech Recognition
In this work, an effective data scheduling strategy for semi- supervised learning (SSL) for acoustic modeling in automatic speech recognition is explored. The conventional approach uses a seed model trained with supervised data to automatically recognize