2022/10/17 by Adnan Haider, Tim Ng, Haider, Adnan +7
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Speech Recognition and Synthesis #Speech and Audio Processing
paper · pdf · doi:10.48550/arxiv.2210.08918
openalex publication_date 2022/10/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models. This paper aims to isolate, identify and bring forward the implicit modelling decisions induced by the design implementation of standard finite state transducer (FST) lattice based MMI training framework. The paper particularly investigates the necessity to maintain a preselected numerator alignment and raises the importance of determinizing FST denominator lattices on the fly. The efficacy of employing on the fly FST lattice determinization is mathematically shown to guarantee discrimination at the hypothesis level and is empirically shown through training deep CNN models on a 18K hours Mandarin dataset and on a 2.8K hours English dataset. On assistant and dictation tasks, the approach achieves between 2.3-4.6% relative WER reduction (WERR) over the standard FST lattice based approach.