Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
arXiv:2104.06104 · doi:10.21437/Interspeech.2021-1671
Abstract
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.
arXiv commentaccepted at Interspeech2021
References in corpus (10)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Sequence Transduction with Recurrent Neural Networks
- Improved training of end-to-end attention models for speech recognition
- A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
- A New Training Pipeline for an Improved Neural Transducer
- Accelerating RNN Transducer Inference via One-Step Constrained Beam Search
- Context-Dependent Acoustic Modeling without Explicit Phone Clustering
- A study of latent monotonic attention variants