模式识别国家重点实验室知识库

Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China

Image search

Paste the image URL

CASIA OpenIR > 模式识别国家重点实验室 > 智能交互

Recent Publications
Downloads
- All
- Month
- Week

CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing [期刊论文, 2022-09]
PIRNet: Personality-Enhanced Iterative Refinement Network for Emotion Recognition .. [期刊论文, 2022-09]
SpecMNet: Spectrum mend network for monaural speech enhancement [期刊论文, 2022-07]
Predicting the Epidemics Trend of COVID-19 Using Epidemiological-Based Generative .. [期刊论文, 2022-07]
普通话语音识别中的神经网络语言模型的比较研究 [会议论文, 2022-06]
Hypersphere Embedding and Additive Margin for Query-by-example Keyword Spotting [会议论文, 2022-06]
Continual Learning for Fake Audio Detection [会议论文, 2022-06]
ParamE: Regarding Neural Network Parameters as Relation Embeddings for Knowledge G.. [会议论文, 2022-06]
Decoupling_Pronunciation_and_Language_for_End-to-End_Code-Switching_Automatic_Spee.. [会议论文, 2022-06]
End-to-End Spelling Correction Conditioned on Acoustic Feature for Code-switching .. [会议论文, 2022-06]

1. MEC 2017: Multimodal Emotion Recognition Challenge

[1115]

2. Deep imitator: handwriting calligraphy imitation via deep attention networks

[80]

3. 语音伪造与鉴伪的发展与挑战

[74]

4. 多语言语音数据库自动优化方法研究

[70]

5. FOCUSING ON ATTENTION: PROSODY TRANSFER AND ADAPTATIVE OPTIMIZATION STRATEGY FOR M..

[70]

6. Micro-Expression Recognition Based on Local Two-Order Gradient Pattern

[63]

7. Multimodal Transformer Learning for Continuous Emotion Recognition

[61]

8. Combining prosodic and spectral features for Mandarin intonation recognition

[57]

9. 基于静音时长和文本特征融合的韵律边界自动标注

[57]

10. Assign stress for interrogative sentences via syntax structure mapping

[53]

1. MEC 2017: Multimodal Emotion Recognition Challenge

[47]

2. CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandari..

[5]

3. Language-Adversarial Transfer Learning for Low-Resource Speech Recognition

[4]

4. 基于深度学习语音分离技术的研究现状与进展

[4]

5. Robust Text Image Recognition via Adversarial Sequence-to-Sequence Domain Adaptati..

[3]

6. 端到端中英混合语音识别方法研究

[3]

7. Deep imitator: handwriting calligraphy imitation via deep attention networks

[2]

8. End-to-End Post-Filter for Speech Separation With Deep Attention Fusion Features

[2]

9. Adversarial Multilingual Training for Low-Resource Speech Recognition

[2]

10. 基于语言知识迁移的端到端语音识别方法研究

[2]

1. MEC 2017: Multimodal Emotion Recognition Challenge

[4]

2. CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandari..

[3]

3. End-to-End Post-Filter for Speech Separation With Deep Attention Fusion Features

[2]

4. Adversarial Multilingual Training for Low-Resource Speech Recognition

[2]

5. Hierarchical stress modeling in Mandarin text-to-speech

[1]

6. Continuous multimodal emotion prediction based on long short term memory recurrent..

[1]

7. 基于内容和声学特征层级融合的自动韵律边界标注

[1]

8. Discriminative Learning for Monaural Speech Separation Using Deep Embedding Featur..

[1]

9. Multimodal Spatiotemporal Representation for Automatic Depression Level Detection

[1]

10. Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recogni..

[1]

Authors & Scholar Pages

Total Items22834
Fulltexts11261
Views3384623
Downloads461591