Dynamic curriculum learning via data parameters for noise robust keyword spotting
| Autor: | Tien Dung Tran, Takuya Higuchi, Masood Delfarah, Shreyas Saxena, Mehrez Souden, Chandra Shekhar Dhir |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Sound (cs.SD) Noise measurement business.industry Computer science Computer Science - Artificial Intelligence Acoustic model Image processing Machine learning computer.software_genre Computer Science - Sound Data modeling Machine Learning (cs.LG) Reduction (complexity) Noise Artificial Intelligence (cs.AI) Audio and Speech Processing (eess.AS) Keyword spotting FOS: Electrical engineering electronic engineering information engineering Artificial intelligence Gradient descent business computer Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | ICASSP |
| DOI: | 10.48550/arxiv.2102.09666 |
| Popis: | We propose dynamic curriculum learning via data parameters for noise robust keyword spotting. Data parameter learning has recently been introduced for image processing, where weight parameters, so-called data parameters, for target classes and instances are introduced and optimized along with model parameters. The data parameters scale logits and control importance over classes and instances during training, which enables automatic curriculum learning without additional annotations for training data. Similarly, in this paper, we propose using this curriculum learning approach for acoustic modeling, and train an acoustic model on clean and noisy utterances with the data parameters. The proposed approach automatically learns the difficulty of the classes and instances, e.g. due to low speech to noise ratio (SNR), in the gradient descent optimization and performs curriculum learning. This curriculum learning leads to overall improvement of the accuracy of the acoustic model. We evaluate the effectiveness of the proposed approach on a keyword spotting task. Experimental results show 7.7% relative reduction in false reject ratio with the data parameters compared to a baseline model which is simply trained on the multiconditioned dataset. Comment: Accepted at ICASSP 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|