English
Related papers

Related papers: Minimization of Streaming Transducers

200 papers

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 John Yang , Le An , Su Inn Park

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small…

Computation and Language · Computer Science 2023-12-18 Antoine Bruguier , David Qiu , Yanzhang He

Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output…

Machine Learning · Computer Science 2016-08-08 Navdeep Jaitly , David Sussillo , Quoc V. Le , Oriol Vinyals , Ilya Sutskever , Samy Bengio

In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the Transformers. Although self-attention mechanism provides a means to exploit long…

Computation and Language · Computer Science 2021-04-06 Tze Yuang Chong , Xuyang Wang , Lin Yang , Junjie Wang

Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve learning under low data regimes. However, most works have…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Andrés Villa , Juan-Manuel Perez-Rua , Victor Escorcia , Vladimir Araujo , Juan Carlos Niebles , Alvaro Soto

We show that fundamental learning tasks, such as finding an approximate linear separator or linear regression, require memory at least \emph{quadratic} in the dimension, in a natural streaming setting. This implies that such problems cannot…

Machine Learning · Computer Science 2019-06-13 Yuval Dagan , Gil Kur , Ohad Shamir

In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…

Computation and Language · Computer Science 2019-09-30 Jinyu Li , Rui Zhao , Hu Hu , Yifan Gong

Motivated by a need to characterize transient behaviors in large network systems in terms of relevant signal norms and worst-case input scenarios, we propose a novel approach based on existing theory for matrix pseudospectra. We extend…

Optimization and Control · Mathematics 2022-10-18 Jonas Hansson , Emma Tegling

Piecewise Linear Approximation (PLA) is a well-established tool to reduce the size of the representation of time series by approximating the series by a sequence of line segments while keeping the error introduced by the approximation…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-10-10 Romaric Duvignau , Vincenzo Gulisano , Marina Papatriantafilou , Vladimir Savic

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Artificial Intelligence · Computer Science 2023-06-28 Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

Short text classification is a crucial and challenging aspect of Natural Language Processing. For this reason, there are numerous highly specialized short text classifiers. However, in recent short text research, State of the Art (SOTA)…

Computation and Language · Computer Science 2023-08-14 Fabian Karl , Ansgar Scherp

We investigate the tree-to-tree functions computed by "affine $\lambda$-transducers": tree automata whose memory consists of an affine $\lambda$-term instead of a finite state. They can be seen as variations on Gallot, Lemay and Salvati's…

Formal Languages and Automata Theory · Computer Science 2026-03-13 Lê Thành Dũng Nguyên , Gabriele Vanoni

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-14 Bo Li , Shuo-yiin Chang , Tara N. Sainath , Ruoming Pang , Yanzhang He , Trevor Strohman , Yonghui Wu

Automata-logic connections are pillars of the theory of regular languages. Such connections are harder to obtain for transducers, but important results have been obtained recently for word-to-word transformations, showing that the three…

Formal Languages and Automata Theory · Computer Science 2016-06-02 Luc Dartois , Emmanuel Filiot , Pierre-Alain Reynier , Jean-Marc Talbot

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…

Computation and Language · Computer Science 2026-03-13 Youness Dkhissi , Valentin Vielzeuf , Elys Allesiardo , Anthony Larcher

We consider the problem of evaluating in streaming (i.e., in a single left-to-right pass) a nested word transduction with a limited amount of memory. A transduction T is said to be height bounded memory (HBM) if it can be evaluated with a…

Formal Languages and Automata Theory · Computer Science 2023-06-22 Emmanuel Filiot , Olivier Gauwin , Pierre-Alain Reynier , Frédéric Servais

Low-tubal-rank tensor approximation has been proposed to analyze large-scale and multi-dimensional data. However, finding such an accurate approximation is challenging in the streaming setting, due to the limited computational resources. To…

Machine Learning · Computer Science 2021-08-24 Qianxin Yi , Chenhao Wang , Kaidong Wang , Yao Wang

Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting…

Computation and Language · Computer Science 2016-06-22 James Cross , Liang Huang

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Alejandro Gomez-Alanis , Lukas Drude , Andreas Schwarz , Rupak Vignesh Swaminathan , Simon Wiesler
‹ Prev 1 4 5 6 7 8 10 Next ›