Saved in:
Bibliographic Details
Main Authors: Ando, Atsushi, Moriya, Takafumi, Horiguchi, Shota, Masumura, Ryo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.18910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929401733578752
author Ando, Atsushi
Moriya, Takafumi
Horiguchi, Shota
Masumura, Ryo
author_facet Ando, Atsushi
Moriya, Takafumi
Horiguchi, Shota
Masumura, Ryo
contents This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only speaking-style factor terms but also syntax words, which disturbs learning speaking-style information. To solve this problem, we introduce factor-conditioned captioning (FCC), which first outputs a phrase representing speaking-style factors (e.g., gender, pitch, etc.), and then generates a caption to ensure the model explicitly learns speaking-style factors. We also propose greedy-then-sampling (GtS) decoding, which first predicts speaking-style factors deterministically to guarantee semantic accuracy, and then generates a caption based on factor-conditioned sampling to ensure diversity. Experiments show that FCC outperforms the original caption-based training, and with GtS, it generates more diverse captions while keeping style prediction performance.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18910
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Factor-Conditioned Speaking-Style Captioning
Ando, Atsushi
Moriya, Takafumi
Horiguchi, Shota
Masumura, Ryo
Computation and Language
Sound
Audio and Speech Processing
This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only speaking-style factor terms but also syntax words, which disturbs learning speaking-style information. To solve this problem, we introduce factor-conditioned captioning (FCC), which first outputs a phrase representing speaking-style factors (e.g., gender, pitch, etc.), and then generates a caption to ensure the model explicitly learns speaking-style factors. We also propose greedy-then-sampling (GtS) decoding, which first predicts speaking-style factors deterministically to guarantee semantic accuracy, and then generates a caption based on factor-conditioned sampling to ensure diversity. Experiments show that FCC outperforms the original caption-based training, and with GtS, it generates more diverse captions while keeping style prediction performance.
title Factor-Conditioned Speaking-Style Captioning
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.18910