ORCIDGitHubLinkedIn
RSS Curriculum Vitae TR

RNN-T

Turkish equivalent: Tekrarlayan sinir ağı dönüştürücüsüDomain: Speech Processing

Recurrent Neural Network Transducer, an end-to-end streaming ASR architecture that jointly models acoustic input and output-token history through a transducer objective.

  • Automatic Speech Recognition
  • Streaming ASR
  • Beam Search
  • Connectionist Temporal Classification

Source

  • https://arxiv.org/abs/1211.3711

Updated:

Related concepts

Speech Processing