About this document
End-to-End ASR Techniques Overview by api-332129590 is a document available to read on EtoBox.
The document discusses end-to-end automatic speech recognition. It mentions two popular open-source toolkits, ESPnet and Eesen, for building end-to-end ASR systems. ESPnet is based on Chainer and PyTorch and follows the Kaldi toolkit for data processing and recipes. Eesen is based on Kaldi but uses bidirectional RNNs/LSTMs with CTC training. It also discusses using Kaldi for end-to-end ASR with TensorFlow integration. Finally, it reviews several papers on end-to-end approaches using CNNs and RNNs with diffe
- Author
- api-332129590
- Language
- EN