mlsanityData to 7 Oct 2026

Conformer-based Hybrid ASR System for Switchboard Dataset

arXiv 2111.03442 ↗First posted 5 Nov 2021cs.CL eess.AS stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer acoustic model for hybrid ASR is not investigated. In this paper, we present and evaluate a competitive conformer-based hybrid model training recipe. We study different training aspects and methods to improve word-error-rate as well as to increase training speed. We apply time downsampling methods for efficient training and use transposed convolutions to upsample the output sequence again. We conduct experiments on Switchboard 300h dataset and our conformer-based hybrid model achieves competitive results compared to other architectures. It generalizes very well on Hub5'01 test set and outperforms the BLSTM-based hybrid model significantly.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

22 of 40 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  7. 2015Listen, Attend and Spellcited by 542
  8. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 96
  9. 2019Transformer-based Acoustic Modeling for Hybrid Speech Recognitioncited by 86
  10. 2019RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentationcited by 63
  11. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  12. 2020Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboardcited by 36
10 more
  1. 2018RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognitioncited by 30
  2. 2021On the limit of English conversational speech recognitioncited by 30
  3. 2018Self-Attentional Acoustic Modelscited by 29
  4. 2019Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networkscited by 24
  5. 2020Phoneme Based Neural Transducer for Large Vocabulary Speech Recognitioncited by 20
  6. 2020The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugmentcited by 19
  7. 2019Cumulative Adaptation for BLSTM Acoustic Modelscited by 11
  8. 2019LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoringcited by 11
  9. 2016A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognitioncited by 10
  10. 2021Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognitioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 2; 2025: 3; 2026: 2.

15 papers.

Sort:

By area:

  1. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  2. 2022Improving the Training Recipe for a Robust Conformer-based Hybrid Modelcited by 9
  3. 2024Serialized Output Training by Learned Dominancecited by 5
  4. 2023Comparative Analysis of the wav2vec 2.0 Feature Extractorcited by 4
  5. 2022Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speechcited by 3
  6. 2023Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognitioncited by 3
  7. 2025Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filteringcited by 3
  8. 2025How to Evaluate Speech Translation with Source-Aware Neural MT Metricscited by 3
  9. 2023Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillationcited by 2
  10. 2023Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Projectcited by 2
  11. 2024Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clientscited by 1
  12. 2026Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognitioncited by 1
3 more
  1. 2023Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systemscited by 0
  2. 2025Towards Hardware Supported Domain Generalization in DNN-Based Edge Computing Devices for Health Monitoringcited by 0
  3. 2026SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studiescited by 0