paper-with-me

홈 › Papers

Polynomial Mixing for Efficient Self-supervised Speech Encoders

2026-02-28 · Eva Feillet, Ryan Whetten, David Picard, Alexandre Allauzen arxiv

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes significant constraints on scalability. In this work, we propose a novel token-mixing mechanism, the Polynomial Mixer (PoM), as a drop-in replacement for multi-head self-attention. PoM computes a polynomial representation of the input with linear complexity with respect to the input sequence length. We integrate PoM into a self-supervised speech representation learning framework based on BEST-RQ and evaluate its performance on downstream speech recognition tasks. Experimental results demonstrate that PoM achieves a competitive word error rate compared to full self-attention and other linear-complexity alternatives, offering an improved trade-off between performance and efficiency in time and memory.

📄 PDF Abstract BibTeX arXiv:2603.00683

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSpeech Recognition

Similar Papers 제목 키워드 기반

Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency

2023-11-05 · Sungho Jeon, Ching-Feng Yeh, Hakan Inan, Wei-Ning Hsu 외

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers …

Quantization

Self-Remixing: Unsupervised Speech Separation via Separation and Remixing

2022-11-18 · Kohei Saijo, Tetsuji Ogawa

We present Self-Remixing, a novel self-supervised speech separation method, which refines a pre-trained separation model in an unsupervised manner. The proposed method consists of a shuffler module and a solver module, a…

Domain AdaptationSemi-supervised Domain AdaptationSpeech Separation

Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition

2026-02-04 · Aditya Srinivas Menon, Kumud Tripathi, Raj Gohil, Pankaj Wasnik arxiv

Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as a linear-time alternative that summarize…

Self-Supervised LearningSpeech Recognition

Introducing Semantics into Speech Encoders

2022-11-15 · Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim 외

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM)…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Entity Resolutionintent-classification+10

Continual self-training with bootstrapped remixing for speech enhancement

2021-10-19 · Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu 외

We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies includin…

Domain AdaptationSpeech EnhancementUnsupervised Domain Adaptation