mlsanityData to 14 Oct 2026

Streaming Speech-to-Confusion Network Speech Recognition

arXiv 2306.03778 ↗First posted 2 Jun 2023eess.AS cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming ASR architecture that outputs a confusion network while maintaining limited latency, as needed for interactive applications. We show that 1-best results of our model are on par with a comparable RNN-T system, while the richer hypothesis set allows second-pass rescoring to achieve 10-20% lower word error rate on the LibriSpeech task. We also show that our model outperforms a strong RNN-T baseline on a far-field voice assistant task.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

20 of 25 references.

References · 20

  1. 2016Layer Normalizationcited by 5,669
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  4. 2015Listen, Attend and Spellcited by 543
  5. 2015Attention-Based Models for Speech Recognitioncited by 401
  6. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 235
  7. 2020Contextual RNN-T For Open Domain ASRcited by 85
  8. 2020Streaming automatic speech recognition with the transformer modelcited by 73
  9. 2020FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularizationcited by 69
  10. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  11. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  12. 2020Improved Mask-CTC for Non-Autoregressive End-to-End ASRcited by 32
8 more
  1. 2020Transformer-based Online CTC/attention End-to-End Speech Recognition Architecturecited by 28
  2. 2020Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Mergingcited by 26
  3. 2019Synchronous Transformers for End-to-End Speech Recognitioncited by 24
  4. 2020Low Latency End-to-End Streaming Speech Recognition with a Scout Networkcited by 20
  5. 2021Streaming End-to-End ASR based on Blockwise Non-Autoregressive Modelscited by 11
  6. 2022Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systemscited by 5
  7. 2019Towards Online End-to-end Transformer Automatic Speech Recognitioncited by 3
  8. 2022VQ-T: RNN Transducers using Vector-Quantized Prediction Network Statescited by 3

Built on by

Not cited yet.