Advances in All-Neural Speech Recognition
Not on the map. Why?
Abstract (arXiv)
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a cleaner version. We present a number of stabilization and initialization methods we have found useful in training these networks. We evaluate our system on the commonly used NIST 2000 conversational telephony test set, and significantly exceed the previously published performance of similar systems, both with and without the use of an external language model and decoding technology.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Sep 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5.
5 papers.
- 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
- 2021Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Unitscited by 13
- 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillationcited by 12
- 2021End-to-End Automatic Speech Recognition with Deep Mutual Learningcited by 1
- 2021Exploring CTC Based End-to-End Techniques for Myanmar Speech Recognitioncited by 0
- 2021Recent Advances in End-to-End Automatic Speech Recognition2 Nov 2021
- 2021Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units8 Oct 2021
- 2021Exploring CTC Based End-to-End Techniques for Myanmar Speech Recognition13 May 2021
- 2021End-to-End Automatic Speech Recognition with Deep Mutual Learning16 Feb 2021
- 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillation16 Feb 2021