mlsanityData to 7 Oct 2026

A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition

arXiv 2210.00367 ↗First posted 1 Oct 2022eess.AS cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Phoneme recognition is a very important part of speech recognition that requires the ability to extract phonetic features from multiple frames. In this paper, we compare and analyze CNN, RNN, Transformer, and Conformer models using phoneme recognition. For CNN, the ContextNet model is used for the experiments. First, we compare the accuracy of various architectures under different constraints, such as the receptive field length, parameter size, and layer depth. Second, we interpret the performance difference of these models, especially when the observable sequence length varies. Our analyses show that Transformer and Conformer models benefit from the long-range accessibility of self-attention through input frames.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

27 of 39 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2021Transformers in Vision: A Surveycited by 1,009
  6. 2020On Layer Normalization in the Transformer Architecturecited by 906
  7. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  8. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  9. 2022How Do Vision Transformers Work?cited by 305
  10. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 293
  11. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  12. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 232
15 more
  1. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  2. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 196
  3. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  4. 2021Unsupervised Speech Recognitioncited by 147
  5. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 96
  6. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 93
  7. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  8. 2020On the Comparison of Popular End-to-End Models for Large Scale Speech Recognitioncited by 62
  9. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 61
  10. 2019SpecAugment on Large Scale Datasetscited by 60
  11. 2021What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structurecited by 52
  12. 2019Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutionscited by 27
  13. 2020Probing Acoustic Representations for Phonetic Propertiescited by 26
  14. 2020Understanding Self-Attention of Self-Supervised Audio Transformerscited by 15
  15. 2022Similarity and Content-based Phonetic Self Attention for Speech Recognitioncited by 3

Built on by

Not cited yet.