mlsanityData to 14 Oct 2026

Espresso: A Fast End-to-end Neural Speech Recognition Toolkit

arXiv 1909.08723 ↗First posted 18 Sep 2019cs.CL cs.SD eess.AScited by 31

Not on the map. Why?

Abstract (arXiv)

We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 9; 2023: 4; 2024: 3.

31 papers.

Sort:

  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  2. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  3. 2023End-to-End Speech Recognition: A Surveycited by 129
  4. 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durationscited by 58
  5. 2021Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognitioncited by 16
  6. 2021Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usabilitycited by 14
  7. 2021Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstructioncited by 13
  8. 2021Sequential Randomized Smoothing for Adversarially Robust Speech Recognitioncited by 13
  9. 2022Multi-blank Transducers for Speech Recognitioncited by 11
  10. 2021End2End Acoustic to Semantic Transductioncited by 10
  11. 2021Wake Word Detection with Streaming Transformerscited by 10
  12. 2024Label-Looping: Highly Efficient Decoding for Transducerscited by 9
19 more
  1. 2021Multi-Channel Multi-Speaker ASR Using 3D Spatial Featurecited by 7
  2. 2021Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognitioncited by 6
  3. 2021Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic modelcited by 6
  4. 2022Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Trainingcited by 6
  5. 2022Insights on Neural Representations for End-to-End Speech Recognitioncited by 5
  6. 2022Relaxed Attention for Transformer Modelscited by 5
  7. 2022Training Integer-Only Deep Recurrent Neural Networkscited by 5
  8. 2021Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognitioncited by 4
  9. 2021Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscriptscited by 3
  10. 2021iRNN: Integer-only Recurrent Neural Networkcited by 3
  11. 2023Quran Recitation Recognition using End-to-End Deep Learningcited by 3
  12. 2021Deformable TDNN with adaptive receptive fields for speech recognitioncited by 2
  13. 2022BEA-Base: A Benchmark for ASR of Spontaneous Hungariancited by 2
  14. 2022Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding taskscited by 2
  15. 2022Probing Statistical Representations For End-To-End ASRcited by 1
  16. 2022EFI: A Toolbox for Feature Importance Fusion and Interpretation in Pythoncited by 0
  17. 2023RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarioscited by 0
  18. 2024Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognitioncited by 0
  19. 2024Improving Autoregressive Training with Dynamic Oraclescited by 0