BASS: Block-wise Adaptation for Speech Summarization

Roshan Sharma, Kenneth Zheng, Siddhant Arora, Shinji Watanabe, Rita Singh +1 more
7/17/2023
cs.CLcs.SDeess.AS

No official code found. Best implementation: JaeeonPark/BASS (0 stars, last commit 2026-01-02).

Abstract

End-to-end speech summarization has been shown to improve performance over cascade baselines. However, such models are difficult to train on very large inputs (dozens of minutes or hours) owing to compute restrictions and are hence trained with truncated model inputs. Truncation leads to poorer models, and a solution to this problem rests in block-wise modeling, i.e., processing a portion of the input frames at a time. In this paper, we develop a method that allows one to train summarization models on very long sequences in an incremental manner. Speech summarization is realized as a streaming process, where hypothesis summaries are updated every block based on new acoustic information. We devise and test strategies to pass semantic context across the blocks. Experiments on the How2 dataset demonstrate that the proposed block-wise training method improves by 3 points absolute on ROUGE-L over a truncated input baseline.

View on arXivView PDF

Code Implementations(1)

JaeeonPark/BASSCommunity69%

Implementation of BASS (Block-wise Adaptation for Speech Summarization)

00PythonJan 2, 20269 months ago

Similar Papers

Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation

86% match2024

Investigating Efficiently Extending Transformers for Long Input Summarization

86% match1 repo1.7k2022

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization

86% match2023

Prompting Large Language Models with Audio for General-Purpose Speech Summarization

84% match1 repo202024

An End-to-End Speech Summarization Using Large Language Model

83% match2024

Leveraging Large Text Corpora for End-to-End Speech Summarization

83% match2023

Cite this paper

@article{sharma2023bass,
  title  = {BASS: Block-wise Adaptation for Speech Summarization},
  author = {Roshan Sharma and Kenneth Zheng and Siddhant Arora and Shinji Watanabe and Rita Singh and Bhiksha Raj},
  year   = {2023},
  eprint = {2307.08217},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.08217v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.08217.svg)](https://codeofpaper.com/paper/2307.08217)

Discussion