Attention-based End-to-end Speech Recognition On Voice Search

Abstract

Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempts have shown that applying attention-based encoder-decoder to Mandarin speech recognition was quite difficult due to the logographic orthography of Mandarin, the large vocabulary and the conditional dependency of the attention model. In this paper, we use character embedding to deal with the large vocabulary. Several tricks are used for effective model training, including L2 regularization, Gaussian weight noise and frame skipping. We compare two attention mechanisms and use attention smoothing to cover long context in the attention model. Taken together, these tricks allow us to finally achieve a character error rate (CER) of 3.58% and a sentence error rate (SER) of 7.43% on the MiTV voice

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshan2017attention

Related papers

• Mmspeech: Multi-modal Multi-task Encoder-decoder Pre-training For Speech Recognition (2022)6.34
• Towards End-to-end Code-switching Speech Recognition (2018)0.00
• Joint Ctc-attention Based End-to-end Speech Recognition Using Multi-task Learning (2016)20.43
• Pronunciation-aware Unique Character Encoding For RNN Transducer-based Mandarin Speech Recognition (2022)3.58
• Research On Modeling Units Of Transformer Transducer For Mandarin Speech Recognition (2020)0.00
• Effectiveasr: A Single-step Non-autoregressive Mandarin Speech Recognition Architecture With High Accuracy And Inference Speed (2024)3.58
• Towards A Competitive End-to-end Speech Recognition For Chime-6 Dinner Party Transcription (2020)6.77
• Advances In Joint Ctc-attention Based End-to-end Speech Recognition With A Deep CNN Encoder And RNN-LM (2017)16.49