Fast Context-biasing For CTC And Transducer ASR Models With Ctc-based Word Spotter
2024 · Andrei Andrusenko, Aleksandr Laptev, Vladimir Bataev, et al.
Abstract
Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modification of the ASR model or the beam-search decoding algorithm, complicating model reuse and slowing down inference. This work presents a new approach to fast context-biasing with CTC-based Word Spotter (CTC-WS) for CTC and Transducer (RNN-T) ASR models. The proposed method matches CTC log-probabilities against a compact context graph to detect potential context-biasing candidates. The valid candidates then replace their greedy recognition counterparts in corresponding frame intervals. A Hybrid Transducer-CTC model enables the CTC-WS application for the Transducer model. The results demonstrate a significant acceleration of the context-biasing recognition with a simultaneous improvement in F-score and WER compared to baseline methods. The proposed method is publicly available in the NVIDIA NeMo toolkit.
Authors
(none)
Tags
Stats
Related papers
- Adaptive Contextual Biasing For Transducer Based Streaming Speech Recognition (2023)7.16
- End-to-end Contextual Asr Based On Posterior Distribution Adaptation For Hybrid Ctc/attention System (2022)0.00
- Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages (2023)4.52
- Towards Personalization Of CTC Speech Recognition Models With Contextual Adapters And Adaptive Boosting (2022)0.00
- Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition (2023)8.60
- Locality Enhanced Dynamic Biasing And Sampling Strategies For Contextual ASR (2024)0.00
- Improving Neural Biasing For Contextual Speech Recognition By Early Context Injection And Text Perturbation (2024)8.09
- DCCRN-KWS: An Audio Bias Based Model For Noise Robust Small-footprint Keyword Spotting (2023)5.24