.png){kind=icon}
返回
Deep temporal representation learning for language identification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106921.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Language identification (LID) is a key component in downstream tasks. Recently, the self-supervised speech representation learned by Wav2Vec 2.0 (W2V2) has been demonstrated to be very effective for various speech- related tasks. In LID, it is commonly used as a feature extractor for frame-level feature extraction. However, there is currently no effective method for extracting temporal information from frame-level features to enhance the performance of LID systems. To deal with this issue, we propose a LID framework based on deep temporal representation (DTR) learning. First, the W2V2 model is used as a front-end feature extractor. This model can capture contextual representations from continuous raw audio in which temporal dependencies are embedded. Then, a temporal network responsible for learning temporal dependencies is proposed to process the output of W2V2. This temporal network comprises a temporal representation extractor for extracting utterance-level representations and a temporal regularization term to impose constraints on temporal dynamics. Finally, the temporal dependencies are used as utterance-level representations for the subsequent classification. The proposed DTR method is evaluated on the OLR2020 database and compared to other state-of-the-art methods. The results show that the proposed method achieves decent experimental performance on all the three tasks of OLR2020 database.
Keyword:
Language identification
Temporal representation learning
Temporal regularization
Wav2Vec 2.0
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
暂无机构信息
引用论文
Efficient Self-Supervised Learning Representations for Spoken Language Identification用于口语识别的高效自监督学习表示
OAAI
OAAI分享收藏ENDÜSTRİYEL DOMATES ATIKLARINDAN KAROTENOİD EKSTRAKSİYONUNUN YANIT YÜZEY YÖNTEMİ İLE OPTİMİZASYONU.png)
GıdaOAAI
GıdaIF0
OAAI分享收藏A simple method to retrieve the complex eigenfrequency of the Earth's nearly diurnal-free wobble; application to the Strasbourg superconducting gravimeter data一种提取地球近周日自由摆动复本征频率的简单方法；应用于斯特拉斯堡超导重力仪数据
OAAI
OAAI分享收藏Genomic scan of endangered moroccan endemic trees (Argania spinosa L. Skeels) along a latitudinal gradient: Exploring gene-environment correlations对濒危摩洛哥特有树种(Argania spinosa L. Skeels)沿纬度梯度的基因组扫描：探究基因-环境相关性OAAI
OAAI分享收藏
查看更多内容