Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
This work addresses efficiency and performance bottlenecks in neural transducer training for speech recognition, offering incremental improvements over existing methods.
The paper tackled the lack of lattice-free sequence discriminative training methods in RNN-Transducers for automatic speech recognition, proposing three such objectives that achieved up to 6.5% relative improvement in word error rate and 40%-70% training time speedup with minimal performance degradation.
Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.