paper-with-me

홈 › Papers

Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMI

2021-12-05 · Jinchuan Tian, Jianwei Yu, Chao Weng, Shi-Xiong Zhang, Dan Su, Dong Yu, Yuexian Zou

Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (LF-MMI), as one of the discriminative training criteria that show superior performance in hybrid ASR systems, is rarely adopted in E2E ASR frameworks. In this work, we propose a novel approach to integrate LF-MMI criterion into E2E ASR frameworks in both training and decoding stages. The proposed approach shows its effectiveness on two of the most widely used E2E frameworks including Attention-Based Encoder-Decoders (AEDs) and Neural Transducers (NTs). Experiments suggest that the introduction of the LF-MMI criterion consistently leads to significant performance improvements on various datasets and different E2E ASR frameworks. The best of our models achieves competitive CER of 4.1\% / 4.4\% on Aishell-1 dev/test set; we also achieve significant error reduction on Aishell-2 and Librispeech datasets over strong baselines.

📄 PDF Abstract BibTeX arXiv:2112.02498

Code (1)

jctian98/e2e_lfmmi 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR

2024-03-16 · Savitha Murthy, Dinkar Sitaram

This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is insufficient for generating inclusive lattices. We minimally…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition

2017-11-15 · Shankar Kumar, Michael Nirschl, Daniel Holtmann-Rice, Hank Liao 외

Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models ar…

speech-recognitionSpeech Recognition

Integrating Lattice-Free MMI into End-to-End Speech Recognition

2022-03-29 · Jinchuan Tian, Jianwei Yu, Chao Weng, Yuexian Zou 외

In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the perform…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Transformer-based language modeling and decoding for conversational speech recognition

2020-01-04 · Kareem Nassar

We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to …

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Lattice-based Improvements for Voice Triggering Using Graph Neural Networks

2020-01-25 · Pranay Dighe, Saurabh Adya, Nuoyu Li, Srikanth Vishnubhotla 외

Voice-triggered smart assistants often rely on detection of a trigger-phrase before they start listening for the user request. Mitigation of false triggers is an important aspect of building a privacy-centric non-intrusi…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition