Meeting Presentation
日 期 時 間 地 點 演講者 主 題 投影片

  Meeting 歷 史 紀 錄 

All 
Meeting Presentation
日 期 時 間 演講者 主 題 投影片
2020/10/29
(四)
上午09:30:00
憶年
Sentiment and Emotion help Sarcasm? A Multi-task Learning Framework for Multi-Modal Sarcasm, Sentiment and Emotion Analysis
2020/09/17
(四)
上午09:30:00
憶年
Enhanced Twitter Sentiment Classification Using Contextual Information
2020/08/27
(四)
上午09:30:00
琬婷
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
2020/08/13
(四)
上午09:30:00
俊良
Personal VAD: Speaker-Conditioned Voice Activity Detection
2020/08/13
(四)
上午09:30:00
宇森
PREDICTING-DETECTION-FILTERS-FOR-SMALL-FOOTPRINT-OPEN-VOCABULARY
2020/07/30
(四)
上午09:30:00
憶年
A Semantics-Based Measure of Emoji Similarity
2020/07/23
(四)
上午09:30:00
琬婷
tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection
2020/06/18
(四)
上午09:30:00
俊良
DISENTANGLED SPEECH EMBEDDINGS USING CROSS-MODAL SELF-SUPERVISION
2020/06/18
(四)
上午09:30:00
宇森
[ICASSP 2020]In defence of metric learning for speaker recognition
2020/05/21
(四)
上午09:30:00
琬婷
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
2020/05/07
(四)
上午09:30:00
韋廷
E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION
2020/05/07
(四)
上午09:30:00
福安
TASNET: TIME-DOMAIN AUDIO SEPARATION NETWORK FOR REAL-TIME, SINGLE-CHANNEL SPEECH SEPARATION
2020/04/30
(四)
上午09:30:00
宇森
STREAM-ATTENTION-BASE-MULTI-ARRAY-END-TO-END-SPEECH-RECOGNITION
2020/04/16
(四)
上午09:30:00
俊良
Speaker Diarization with LSTM
2020/04/16
(四)
上午09:30:00
憶年
Learning Emoji Embeddings using Emoji Co-occurrence Network Graph
2020/04/09
(四)
上午10:00:00
紹瑋
Learning Knowledge Graphs for Question Answering through Conversational Dialog
2020/03/19
(四)
上午09:30:00
琬婷
K-BERT: Enabling Language Representation with Knowledge Graph
2020/03/12
(四)
上午09:30:00
福安
Multi-channel Attention for End-to-End Speech Recognition
2020/03/12
(四)
上午09:30:00
韋廷
TRANSFORMER-ASR-WITH-CONTEXTUAL-BLOCK-PROCESSING
2020/03/05
(四)
上午09:30:00
俊良
Fully Supervised Speaker Diarization
2020/02/06
(四)
上午09:30:00
宇森
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
2020/01/09
(四)
上午09:30:00
憶年
Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
2020/01/09
(四)
上午09:31:00
紹瑋
Revisiting Iterative Relevance Feedback for Document and Passage Retrieval
2019/12/26
(四)
上午09:30:00
琬婷
Question Answering on SQuAD2.0 Dataset
2019/12/25
(三)
上午09:30:00
世弦
Generating Sentences from a Continuous Space
2019/12/19
(四)
上午09:30:00
福安
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
2019/12/19
(四)
上午10:30:00
韋廷
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
2019/12/12
(四)
上午09:30:00
宇森
Improving_Mandarin_Tone_Recognition_Based_on DNN_by_Combining_Acoustic_and_Articulatory_Features_Using_Extended_Recognition_Networks(2)
2019/12/12
(四)
上午10:30:00
百恩
TANDA Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection
2019/12/05
(四)
上午09:30:00
天宏
An improved goodness of pronunciation (GoP) measure for pronunciation evaluation with DNN-HMM system considering HMM transition probabilities

Copyright©2015 SMI Laboratory, NTNU. All rights reserved.