Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
This work clarifies theoretical relationships between modeling architectures in ASR, which is incremental for researchers in speech recognition.
The paper proves that RNN-Transducer models and segmental models (direct HMM) are equivalent in modeling power for automatic speech recognition, showing that blank probabilities correspond to segment length probabilities, and includes initial experiments on decoding strategies.
With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM). While transducer models stay with a frame-level model definition, segmental models are defined on the level of label segments directly. While (soft-)attention-based models avoid explicit alignment, transducer and segmental approach internally do model alignment, either by segment hypotheses or, more implicitly, by emitting so-called blank symbols. In this work, we prove that the widely used class of RNN-Transducer models and segmental models (direct HMM) are equivalent and therefore show equal modeling power. It is shown that blank probabilities translate into segment length probabilities and vice versa. In addition, we provide initial experiments investigating decoding and beam-pruning, comparing time-synchronous and label-/segment-synchronous search strategies and their properties using the same underlying model.