Faster, Simpler And More Accurate Hybrid ASR Systems Using Wordpieces

Abstract

In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-of-the-art results. We then show that using wordpieces as modeling units combined with CTC training, we can greatly simplify the engineering pipeline compared to conventional frame-based cross-entropy training by excluding all the GMM bootstrapping, decision tree building and force alignment steps, while still achieving very competitive word-error-rate. Additionally, using wordpieces as modeling units can significantly improve runtime efficiency since we can use larger stride without losing accuracy. We further confirm these findings on two internal VideoASR datasets: German, which is similar to English as a fusional language, and Turkish, which is an agglutinative language.

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keyzhang2020faster

Related papers

• Advancing CTC-CRF Based End-to-end Speech Recognition With Wordpieces And Conformers (2021)0.00
• An Improved Hybrid Ctc-attention Model For Speech Recognition (2018)0.00
• Hybrid Ctc-attention Based End-to-end Speech Recognition Using Subword Units (2018)10.85
• Transformers With Convolutional Context For ASR (2019)0.00
• Fast Context-biasing For CTC And Transducer ASR Models With Ctc-based Word Spotter (2024)2.26
• CAT: A CTC-CRF Based ASR Toolkit Bridging The Hybrid And The End-to-end Approaches Towards Data Efficiency And Low Latency (2020)9.03
• Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16
• Transformer-based Acoustic Modeling For Hybrid Speech Recognition (2019)16.30