Related papers: Enhancing Monotonic Multihead Attention for Stream…

Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods in machine translation and automatic speech recognition (ASR) tasks. However, the latency of…

Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence. Recent approaches for this task either apply a fixed policy on a state-of-the art Transformer model, or a…

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…

This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, latency was optimised by truncating the online attention weights…

Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we…

This paper works on streaming automatic speech recognition (ASR). Mamba, a recently proposed state space model, has demonstrated the ability to match or surpass Transformers in various tasks while benefiting from a linear complexity…

While attention-based encoder-decoder (AED) models have been successfully extended to the online variants for streaming automatic speech recognition (ASR), such as monotonic chunkwise attention (MoChA), the models still have a large label…

Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention mechanism. However, for trained models, we have previously…

Recently, there has been increasing progress in end-to-end automatic speech recognition (ASR) architecture, which transcribes speech to text without any pre-trained alignments. One popular end-to-end approach is the hybrid Connectionist…

Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in this task. Motivated by…

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

We introduce the Efficient Monotonic Multihead Attention (EMMA), a state-of-the-art simultaneous translation model with numerically-stable and unbiased monotonic alignment estimation. In addition, we present improved training and inference…

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…

Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic…

Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications. Recently proposed Decoder-end Adaptive Computation Steps (DACS) algorithm for online…

The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose…

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…