Related papers: Decoder-only Streaming Transformer for Simultaneou…

Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have showcased strong capabilities in offline translation tasks, applying them to…

Scene Text Recognition (STR) is the problem of recognizing the correct word or character sequence in a cropped word image. To obtain more robust output sequences, the notion of bidirectional STR has been introduced. So far, bidirectional…

Streaming speech translation (StreamST) requires determining appropriate timing, known as policy, to generate translations while continuously receiving source speech inputs, balancing low latency with high translation quality. However,…

This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modeling. In the state-of-the-art…

Audio Visual Scene-aware Dialog (AVSD) is a task to generate responses when discussing about a given video. The previous state-of-the-art model shows superior performance for this task using Transformer-based architecture. However, there…

CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications. In this work, we propose a novel CTC compressor based joint speech and text…

Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure…

Collecting audio-text pairs is expensive; however, it is much easier to access text-only data. Unless using shallow fusion, end-to-end automatic speech recognition (ASR) models require architecture modifications or additional training…

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of…

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this…

Neural machine translation (NMT) typically adopts the encoder-decoder framework. A good understanding of the characteristics and functionalities of the encoder and decoder can help to explain the pros and cons of the framework, and design…

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which…

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve…

There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes available. We study a related problem in which revisions to…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…

Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model. Traditional methods rely on either a fixed wait-$k$ policy coupled with a standalone wait-$k$ translation…

Neural Machine Translation (NMT) leverages one or more trained neural networks for the translation of phrases. Sutskever introduced a sequence to sequence based encoder-decoder model which became the standard for NMT based systems.…

Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only…

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…