paper-with-me

Papers

Improving generalizability of distilled self-supervised speech processing models under distorted settings

2022-10-14 · Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez, Fan-Lin Wang, Liang-Hsuan Tseng, Yu Zhang, Hung-Yi Lee

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar performance as original SSL models, distilled counterparts suffer from performance degradation even more than their original versions in distorted environments. This paper proposes to apply Cross-Distortion Mapping and Domain Adversarial Training to SSL models during knowledge distillation to alleviate the performance gap caused by the domain mismatch problem. Results show consistent performance improvements under both in- and out-of-domain distorted setups for different downstream tasks while keeping efficient model size.

📄 PDF Abstract BibTeX arXiv:2210.07978

Code (1)

nobel861017/distort-robust-distilssl 공식 구현 pytorch

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Ensemble knowledge distillation of self-supervised speech models

2023-02-24 · Kuan-Po Huang, Tzu-hsun Feng, Yu-Kuan Fu, Tsu-Yuan Hsu 외

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we per…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Emotion RecognitionKnowledge Distillation+4

Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning

2021-10-18 · Yi-Chen Chen, Shu-wen Yang, Cheng-Kuang Lee, Simon See 외

Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown that an SSL pretraining model can achieve e…

Multi-Task LearningRepresentation LearningSelf-Supervised LearningSpeech Representation Learning

SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning

2022-10-16 · Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh, Shu-wen Yang 외

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and impleme…

Audio GenerationRepresentation LearningSelf-Supervised LearningSpeaker Recognition+1

Lightweight feature encoder for wake-up word detection based on self-supervised speech representation

2023-03-14 · Hyungjun Lim, Younggwan Kim, Kiho Yeom, Eunjoo Seo 외

Self-supervised learning method that provides generalized speech representations has recently received increasing attention. Wav2vec 2.0 is the most famous example, showing remarkable performance in numerous downstream s…

Dimensionality ReductionSelf-Supervised Learning

SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning

2024-02-26 · Luca Zampierin, Ghouthi Boukli Hacene, Bac Nguyen, Mirco Ravanelli

Self-supervised learning (SSL) has achieved remarkable success across various speech-processing tasks. To enhance its efficiency, previous works often leverage the use of compression techniques. A notable recent attempt …

Knowledge DistillationSelf-Supervised Learning