mlsanityData to 14 Oct 2026

Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System

arXiv 2305.10680 ↗First posted 18 May 2023cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating confidence scores for recognition results is a classic task in ASR field and of vital importance for kinds of downstream tasks and training strategies. Previous end-to-end~(E2E) based confidence estimation models (CEM) predict score sequences of equal length with input transcriptions, leading to unreliable estimation when deletion and insertion errors occur. In this paper we proposed CIF-Aligned confidence estimation model (CA-CEM) to achieve accurate and reliable confidence estimation based on novel non-autoregressive E2E ASR model - Paraformer. CA-CEM utilizes the modeling character of continuous integrate-and-fire (CIF) mechanism to generate token-synchronous acoustic embedding, which solves the estimation failure issue above. We measure the quality of estimation with AUC and RMSE in token level and ECE-U - a proposed metrics in utterance level. CA-CEM gains 24% and 19% relative reduction on ECE-U and also better AUC and RMSE on two test sets. Furthermore, we conduct analysis to explore the potential of CEM for different ASR related usage.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

19 of 29 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  5. 2015Listen, Attend and Spellcited by 543
  6. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 257
  7. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 144
  8. 2019CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognitioncited by 77
  9. 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68
  10. 2019Transformers with convolutional context for ASRcited by 44
  11. 2020Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognitioncited by 35
  12. 2021Why does CTC result in peaky behavior?cited by 33
7 more
  1. 2021ASR Rescoring and Confidence Estimation with ELECTRAcited by 16
  2. 2018Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networkscited by 12
  3. 2021Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASRcited by 12
  4. 2021Residual Energy-Based Models for End-to-End Speech Recognitioncited by 9
  5. 2021Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Predictioncited by 8
  6. 2021Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognitioncited by 7
  7. 2022Confidence Score Based Conformer Speaker Adaptation for Speech Recognitioncited by 5

Built on by

Not cited yet.