Towards Consistent Hybrid HMM Acoustic Modeling

Understand

High-performance hybrid automatic speech recognition (ASR) systems are often trained with clustered triphone outputs, and thus require a complex training pipeline to generate the clustering.

• The same complex pipeline is often utilized in order to generate an alignment for use in frame-wise cross-entropy training.
• In this work, we propose a flat-start factored hybrid model trained by modeling the full set of triphone states explicitly without relying on clustering methods.
• This greatly simplifies the training of new models.