Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation

Author:

Hanbyul Kim, Seunghyun Seo, Lukas Lee, Seolki Baek

Keyword:

Electrical Engineering and Systems Science, Audio and Speech Processing, Audio and Speech Processing (eess.AS), Computation and Language (cs.CL)

journal:

Proc. INTERSPEECH 2023, 1653-1657

date:

2023-06-01 16:00:00

Abstract

Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is particularly desirable but presents a difficult technical challenge. In this work, we propose a method for predicting punctuated text from input speech using a chunk-based Transformer encoder trained with Connectionist Temporal Classification (CTC) loss. The acoustic model trained with long sequences by concatenating the input and target sequences can learn punctuation marks attached to the end of sentences more effectively. Additionally, by combining CTC losses on the chunks and utterances, we achieved both the improved F1 score of punctuation prediction and Word Error Rate (WER).

PDF: Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation.pdf