mlsanityData to 7 Oct 2026

Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition

arXiv 2210.14725 ↗First posted 25 Oct 2022cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an acoustic encoder renders the language model from ground-truth sequences in an auto-regressive manner during training. However, the training corpus of the decoder is limited to the speech transcriptions, which is far less than the corpus needed to train an acceptable language model. This leads to poor robustness of decoder. To alleviate this problem, we propose linguistic-enhanced transformer, which introduces refined CTC information to decoder during training process, so that the decoder can be more robust. Our experiments on AISHELL-1 speech corpus show that the character error rate (CER) is relatively reduced by up to 7%. We also find that in joint CTC-Attention ASR model, decoder is more sensitive to linguistic information than acoustic information.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 25 Oct 2022.

Builds on

21 of 28 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2015Listen, Attend and Spellcited by 542
  5. 2015Attention-Based Models for Speech Recognitioncited by 400
  6. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  7. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  8. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
  9. 2020Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predictcited by 75
  10. 2017Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMcited by 43
  11. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 37
  12. 2016Very Deep Convolutional Networks for End-to-End Speech Recognitioncited by 34
9 more
  1. 2020Improved Mask-CTC for Non-Autoregressive End-to-End ASRcited by 32
  2. 2020Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognitioncited by 24
  3. 2020CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognitioncited by 24
  4. 2018End-to-end Speech Recognition with Word-based RNN Language Modelscited by 23
  5. 2020Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognitioncited by 22
  6. 2021WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognitioncited by 10
  7. 2021Singer Identification Using Deep Timbre Feature Learning with KNN-Netcited by 3
  8. 2022SUSing: SU-net for Singing Voice Synthesiscited by 3
  9. 2018CNN-based MultiChannel End-to-End Speech Recognition for everyday home environmentscited by 2

Built on by

Not cited yet.