paper-with-me

홈 › Papers

SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding

2023-07-12 · Titouan Parcollet, Rogier Van Dalen, Shucong Zhang, Sourav Bhattacharya

Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference and training and increasing memory consumption. Cheaper alternatives to self-attention for ASR have been developed, but they fail to consistently reach the same level of accuracy. This paper, therefore, proposes a novel linear-time alternative to self-attention. It summarises an utterance with the mean over vectors for all time steps. This single summary is then combined with time-specific information. We call this method "SummaryMixing". Introducing SummaryMixing in state-of-the-art ASR models makes it feasible to preserve or exceed previous speech recognition performance while making training and inference up to 28% faster and reducing memory use by half.

📄 PDF Abstract BibTeX arXiv:2307.07421

Code (1)

samsunglabs/summarymixing 공식 구현 pytorch

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition

2024-09-11 · Titouan Parcollet, Rogier Van Dalen, Shucong Zhang, Sourav Batthacharya

Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, incr…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Linear-Complexity Self-Supervised Learning for Speech Processing

2024-07-18 · Shucong Zhang, Titouan Parcollet, Rogier Van Dalen, Sourav Bhattacharya

Self-supervised learning (SSL) models usually require weeks of pre-training with dozens of high-end GPUs. These models typically have a multi-headed self-attention (MHSA) context encoder. However, MHSA takes quadratic ti…

Self-Supervised Learning

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

An Analysis of Linear Complexity Attention Substitutes with BEST-RQ

2024-09-04 · Ryan Whetten, Titouan Parcollet, Adel Moumen, Marco Dinarelli 외

Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due the quadratic complexity of multi-head …

MambaSelf-Supervised Learning

Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer

2026-01-14 · Petros Vavaroutsos, Theodoros Palamas, Pantelis Vikatos arxiv

In recent years, foundation models have become very popular due to their exceptional performance, mainly in natural language (NLP) tasks where they were first introduced. These models usually consist of hundreds of milli…

Self-Supervised LearningInformation RetrievalSpeech Recognition