mlsanityData to 14 Oct 2026

GNCformer Enhanced Self-attention for Automatic Speech Recognition

arXiv 2305.12755 ↗First posted 22 May 2023cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper,an Enhanced Self-Attention (ESA) mechanism has been put forward for robust feature extraction.The proposed ESA is integrated with the recursive gated convolution and self-attention mechanism.In particular, the former is used to capture multi-order feature interaction and the latter is for global feature extraction.In addition, the location of interest that is suitable for inserting the ESA is also worth being explored.In this paper, the ESA is embedded into the encoder layer of the Transformer network for automatic speech recognition (ASR) tasks, and this newly proposed model is named GNCformer. The effectiveness of the GNCformer has been validated using two datasets, that are Aishell-1 and HKUST.Experimental results show that, compared with the Transformer network,0.8%CER,and 1.2%CER improvement for these two mentioned datasets, respectively, can be achieved.It is worth mentioning that only 1.4M additional parameters have been involved in our proposed GNCformer.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

21 of 31 references.

References · 21

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  4. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  5. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  6. 2016Language Modeling with Gated Convolutional Networkscited by 702
  7. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  8. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  9. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 257
  10. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 211
  11. 2020Lite Transformer with Long-Short Range Attentioncited by 127
  12. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
9 more
  1. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  2. 2020RealFormer: Transformer Likes Residual Attentioncited by 62
  3. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  4. 2019Self-Attention Transducers for End-to-End Speech Recognitioncited by 24
  5. 2019Synchronous Transformers for End-to-End Speech Recognitioncited by 24
  6. 2020CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognitioncited by 24
  7. 2020Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognitioncited by 22
  8. 2020Insertion-Based Modeling for End-to-End Automatic Speech Recognitioncited by 13
  9. 2018Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarincited by 6

Built on by

Not cited yet.