Advances In All-neural Speech Recognition

Abstract

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.

Stats

• citations31
• S2 citations—
• github stars0
• HF likes0
• heat score11.29
• arxiv keyzweig2016advances

Related papers

• Advancing CTC-CRF Based End-to-end Speech Recognition With Wordpieces And Conformers (2021)0.00
• BERT Meets CTC: New Formulation Of End-to-end Speech Recognition With Pre-trained Masked Language Model (2022)0.00
• An Improved Hybrid Ctc-attention Model For Speech Recognition (2018)0.00
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Advances In Joint Ctc-attention Based End-to-end Speech Recognition With A Deep CNN Encoder And RNN-LM (2017)16.49
• Advancing Connectionist Temporal Classification With Attention Modeling (2018)11.49
• Improving Non-autoregressive End-to-end Speech Recognition With Pre-trained Acoustic And Language Models (2022)10.07
• Exploring Neural Transducers For End-to-end Speech Recognition (2017)14.90