Boundary And Context Aware Training For Cif-based Non-autoregressive End-to-end ASR

Abstract

Continuous integrate-and-fire (CIF) based models, which use a soft and monotonic alignment mechanism, have been well applied in non-autoregressive (NAR) speech recognition with competitive performance compared with other NAR methods. However, such an alignment learning strategy may suffer from an erroneous acoustic boundary estimation, severely hindering the convergence speed as well as the system performance. In this paper, we propose a boundary and context aware training approach for CIF based NAR models. Firstly, the connectionist temporal classification (CTC) spike information is utilized to guide the learning of acoustic boundaries in the CIF. Besides, an additional contextual decoder is introduced behind the CIF decoder, aiming to capture the linguistic dependencies within a sentence. Finally, we adopt a recently proposed Conformer architecture to improve the capacity of acoustic modeling. Experiments on the open-source Mandarin AISHELL-1 corpus show that the proposed method achi

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keyyu2021boundary

Related papers

• Cif-based Collaborative Decoding For End-to-end Contextual Speech Recognition (2020)9.76
• CIF-T: A Novel Cif-based Transducer Architecture For Automatic Speech Recognition (2023)0.00
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Effectiveasr: A Single-step Non-autoregressive Mandarin Speech Recognition Architecture With High Accuracy And Inference Speed (2024)3.58
• A CTC Alignment-based Non-autoregressive Transformer For End-to-end Automatic Speech Recognition (2023)10.97
• Multilingual Training And Cross-lingual Adaptation On Ctc-based Acoustic Model (2017)0.00
• Attention-based Gated Scaling Adaptative Acoustic Model For Ctc-based Speech Recognition (2019)0.00
• On Lattice-free Boosted MMI Training Of HMM And Ctc-based Full-context ASR Models (2021)7.81