Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept

04/13/2021
by   Wei Zhou, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2023

Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition

Although frame-based models, such as CTC and transducers, have an affini...
research
04/21/2021

Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers

This paper proposes a novel label-synchronous speech-to-text alignment t...
research
05/20/2020

A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition

End-to-end models are gaining wider attention in the field of automatic ...
research
10/26/2022

Monotonic segmental attention for automatic speech recognition

We introduce a novel segmental-attention model for automatic speech reco...
research
07/15/2021

VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording

In this work, we propose novel decoding algorithms to enable streaming a...
research
10/18/2021

Efficient Sequence Training of Attention Models using Approximative Recombination

Sequence discriminative training is a great tool to improve the performa...
research
01/25/2022

Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR

A streaming style inference of encoder-decoder automatic speech recognit...

Please sign up or login with your details

Forgot password? Click here to reset