mlsanityData to 7 Oct 2026

BASS: Block-wise Adaptation for Speech Summarization

arXiv 2307.08217 ↗First posted 17 Jul 2023cs.CL cs.SD eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 17 Jul 2023.

Builds on

20 of 28 references.

References · 20

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2020Longformer: The Long-Document Transformercited by 3,362
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  5. 2018How2: A Large-scale Dataset for Multimodal Language Understandingcited by 137
  6. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 111
  7. 2018Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducercited by 95
  8. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  9. 2020Streaming automatic speech recognition with the transformer modelcited by 73
  10. 2022SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Taskscited by 34
  11. 2017Attention Strategies for Multi-Source Sequence-to-Sequence Learningcited by 32
  12. 2020Streaming Simultaneous Speech Translation with Augmented Memory Transformercited by 30
8 more
  1. 2018Dialog-context aware end-to-end speech recognitioncited by 27
  2. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  3. 2021Speech Summarization using Restricted Self-Attentioncited by 23
  4. 2022Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translationcited by 11
  5. 2023Leveraging Large Text Corpora for End-to-End Speech Summarizationcited by 11
  6. 2021Wake Word Detection with Streaming Transformerscited by 10
  7. 2021Attention-based Multi-hypothesis Fusion for Speech Summarizationcited by 9
  8. 2022XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformerscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Decoder-only Architecture for Streaming End-to-end Speech Recognitioncited by 12
  2. 2025Summarizing Speech: A Comprehensive Surveycited by 5
  3. 2024An End-to-End Speech Summarization Using Large Language Modelcited by 4
  4. 2024Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?cited by 3