paper-with-me

홈 › Papers

Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning

2020-09-24 · Daiki Takeuchi, Yuma Koizumi, Yasunori Ohishi, Noboru Harada, Kunio Kashino

The system we used for Task 6 (Automated Audio Captioning)of the Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge combines three elements, namely, dataaugmentation, multi-task learning, and post-processing, for audiocaptioning. The system received the highest evaluation scores, butwhich of the individual elements most fully contributed to its perfor-mance has not yet been clarified. Here, to asses their contributions,we first conducted an element-wise ablation study on our systemto estimate to what extent each element is effective. We then con-ducted a detailed module-wise ablation study to further clarify thekey processing modules for improving accuracy. The results showthat data augmentation and post-processing significantly improvethe score in our system. In particular, mix-up data augmentationand beam search in post-processing improve SPIDEr by 0.8 and 1.6points, respectively.

📄 PDF Abstract BibTeX arXiv:2009.11436

Code (0)

등록된 구현이 없습니다.

Tasks

Audio captioningData AugmentationMulti-Task Learning

Similar Papers 제목 키워드 기반

Inference-time Scaling for Diffusion-based Audio Super-resolution

2025-08-04 · Yizhu Jin, Zhen Ye, Zeyue Tian, Haohe Liu 외 arxiv

Diffusion models have demonstrated remarkable success in generative tasks, including audio super-resolution (SR). In many applications like movie post-production and album mastering, substantial computational budgets are…

Audio Super-Resolution

Post-Processing Independent Evaluation of Sound Event Detection Systems

2023-06-27 · Janek Ebbers, Reinhold Haeb-Umbach, Romain Serizel

Due to the high variation in the application requirements of sound event detection (SED) systems, it is not sufficient to evaluate systems only in a single operating mode. Therefore, the community recently adopted the po…

Event DetectionSound Event Detection

Frequency effects in Linear Discriminative Learning

2023-06-19 · Maria Heitmeier, Yu-Ying Chuang, Seth D. Axen, R. Harald Baayen

Word frequency is a strong predictor in most lexical processing tasks. Thus, any model of word recognition needs to account for how word frequency effects arise. The Discriminative Lexicon Model (DLM; Baayen et al., 2018…

Incremental Learning

A large-scale study of the effects of word frequency and predictability in naturalistic reading

2019-06-01 · NAACL 2019 6 · Cory Shain

A number of psycholinguistic studies have factorially manipulated words{'} contextual predictabilities and corpus frequencies and shown separable effects of each on measures of human sentence processing, a pattern which …

RetrievalSentence

Modulation Extraction for LFO-driven Audio Effects

2023-05-22 · Christopher Mitcheltree, Christian J. Steinmetz, Marco Comunità, Joshua D. Reiss

Low frequency oscillator (LFO) driven audio effects such as phaser, flanger, and chorus, modify an input signal using time-varying filters and delays, resulting in characteristic sweeping or widening effects. It has been…