| Item type |
SIG Technical Reports(1) |
| 公開日 |
2024-06-07 |
| タイトル |
|
|
タイトル |
Distilling the Class-to-class Distances Encoded in a Classifier to Accelerate DTW of its Posteriorgram |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Distilling the Class-to-class Distances Encoded in a Classifier to Accelerate DTW of its Posteriorgram |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
ポスターセッション2 |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
The University of Tokyo |
| 著者所属 |
|
|
|
The University of Tokyo |
| 著者所属 |
|
|
|
The University of Tokyo |
| 著者所属 |
|
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者所属(英) |
|
|
|
en |
|
|
The University of Tokyo |
| 著者名 |
Haitong, Sun
Jaehyun, Choi
Nobuaki, Minematsu
Daisuke, Saito
|
| 著者名(英) |
Haitong, Sun
Jaehyun, Choi
Nobuaki, Minematsu
Daisuke, Saito
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In media technology, comparison of a sequential data with another is a fundamental technique for many applications, and dynamic time warping is often conducted. Conventionally, two sequences of raw features were compared. These days, more abstract and sequential representations are used, which are obtained with deep neural networks. One of these representations is posteriorgram, where each frame is composed of n-dimensional class posteriors, and frame-to-frame distance is often calculated using a divergence metric such as Bhattacharyya distance. In this study, a novel method is proposed to distill the class-to-class distances encoded in any classifier used to calculate posteriors, and the distances are effectively used to accelerate posteriorgram-based DTW by approximating it as DTW between two sequences of most likely classes. Utterance comparison experiments showed that the proposed method can accelerate the distance calculation step in posteriorgram-based DTW by a factor of 30. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In media technology, comparison of a sequential data with another is a fundamental technique for many applications, and dynamic time warping is often conducted. Conventionally, two sequences of raw features were compared. These days, more abstract and sequential representations are used, which are obtained with deep neural networks. One of these representations is posteriorgram, where each frame is composed of n-dimensional class posteriors, and frame-to-frame distance is often calculated using a divergence metric such as Bhattacharyya distance. In this study, a novel method is proposed to distill the class-to-class distances encoded in any classifier used to calculate posteriors, and the distances are effectively used to accelerate posteriorgram-based DTW by approximating it as DTW between two sequences of most likely classes. Utterance comparison experiments showed that the proposed method can accelerate the distance calculation step in posteriorgram-based DTW by a factor of 30. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AN10442647 |
| 書誌情報 |
研究報告音声言語情報処理（SLP）
巻 2024-SLP-152,
号 57,
p. 1-5,
発行日 2024-06-07
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8663 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-SLP24152057.pdf (5.3 MB)
