| عنوان فارسی مقاله: |
تشخیص همپوشانی گفتار با حافظه کوتاه و بلند مدت شبکه های عصبی بازگشتی |
| عنوان انگلیسی مقاله: | Detecting Overlapping Speech with Long Short-Term Memory Recurrent Neural Networks |
چکیده
1- مقدمه
2 – سیستم تشخیص هم پوشانی
2.1 سیستم مدل پنهان مارکف
2.2. ویژگی های صوتی
3 – حافظه کوتاه و بلند مدت شبکه های عصبی بازگشتی برای تشخیص هم پوشانی
3.1 حافظه کوتاه /بلند مدت-شبکه عصبی برگشتی ها
4. آزمایش
4.1. راه اندازی آزمایشی
4.2 نتایج
نتیجه گیری
کلمات کلیدی :
[PDF]Conference Paperwww.fim.uni-passau.de/fileadmin/files/lehrstuhl/schuller/.../Hagerer17-ELR.pdfby G Hagerer - Cited by 1 - Related articlesThis paper presents a new method for Long Short-Term Memory Recurrent Neural Network (LSTM) based speech overlap detection. To this end, speech overlap data is created artificially by mixing large amounts of speech utterances. Our elaborate training strategies and presented network structures demonstrate ...[PDF]Recurrent Neural Networks for Polyphonic Sound Event Detection in ...https://arxiv.org/pdf/1604.00861by G Parascandolo - 2016 - Cited by 60 - Related articlesApr 4, 2016 - detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent ... for each sound event its category (e.g., music, car, speech), and its beginning and ending. This task is ... a short introduction to RNNs and long short-term memory (LSTM) blocks. We describe in Section 3 ...Enhancing LSTM RNN-Based Speech Overlap Detection by Artificially ...www.aes.org/e-lib/download.cfm?ID=18764by G Hagerer - 2017 - Cited by 1 - Related articlesThis paper presents a new method for Long Short-Term Memory Recurrent Neural Network (LSTM) based speech overlap detection. To this end, speech overlap data is created artificially by mixing large amounts of speech utterances. Our elaborate training strategies and presented network structures demonstrate ...