Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus

08/24/2020
by   Cal Peyser, et al.
0

End-to-end (E2E) automatic speech recognition (ASR) systems lack the distinct language model (LM) component that characterizes traditional speech systems. While this simplifies the model architecture, it complicates the task of incorporating text-only data into training, which is important to the recognition of tail words that do not occur often in audio-text pairs. While shallow fusion has been proposed as a method for incorporating a pre-trained LM into an E2E model at inference time, it has not yet been explored for very large text corpora, and it has been shown to be very sensitive to hyperparameter settings in the beam search. In this work, we apply shallow fusion to incorporate a very large text corpus into a state-of-the-art E2EASR model. We explore the impact of model size and show that intelligent pruning of the training set can be more effective than increasing the parameter count. Additionally, we show that incorporating the LM in minimum word error rate (MWER) fine tuning makes shallow fusion far less dependent on optimal hyperparameter settings, reducing the difficulty of that tuning problem.

READ FULL TEXT
02/09/2021

BembaSpeech: A Speech Recognition Corpus for the Bemba Language

We present a preprocessed, ready-to-use automatic speech recognition cor...
04/09/2021

Language model fusion for streaming end to end speech recognition

Streaming processing of speech audio is required for many contemporary p...
05/19/2020

Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion

Proper nouns present a challenge for end-to-end (E2E) automatic speech r...
07/26/2021

Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruning

We introduce an unsupervised approach for correcting highly imperfect sp...
05/18/2022

Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator

Contextual knowledge is essential for reducing speech recognition errors...
10/06/2021

Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition

Text-only adaptation of an end-to-end (E2E) model remains a challenging ...
06/17/2021

Layer Pruning on Demand with Intermediate CTC

Deploying an end-to-end automatic speech recognition (ASR) model on mobi...