Simplified End-to-end MMI Training And Voting For ASR

Abstract

A simplified speech recognition system that uses the maximum mutual information (MMI) criterion is considered. End-to-end training using gradient descent is suggested, similarly to the training of connectionist temporal classification (CTC). We use an MMI criterion with a simple language model in the training stage, and a standard HMM decoder. Our method compares favorably to CTC in terms of performance, robustness, decoding time, disk footprint and quality of alignments. The good alignments enable the use of a straightforward ensemble method, obtained by simply averaging the predictions of several neural network models, that were trained separately end-to-end. The ensemble method yields a considerable reduction in the word error rate.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfritz2017simplified

Related papers

• Consistent Training And Decoding For End-to-end Speech Recognition Using Lattice-free MMI (2021)8.35
• On Lattice-free Boosted MMI Training Of HMM And Ctc-based Full-context ASR Models (2021)7.81
• Audio-attention Discriminative Language Model For ASR Rescoring (2019)9.23
• MIMO-SPEECH: End-to-end Multi-channel Multi-speaker Speech Recognition (2019)13.93
• Incorporating VAD Into ASR System By Multi-task Learning (2021)4.52
• Unsupervised Model-based Speaker Adaptation Of End-to-end Lattice-free MMI Model For Speech Recognition (2022)2.26
• End-to-end Multimodal Speech Recognition (2018)10.21
• Multiple-hypothesis Ctc-based Semi-supervised Adaptation Of End-to-end Speech Recognition (2021)5.84