相关论文: DuoTok: Source-Aware Dual-Track Tokenization for M…

We introduce a Multi-modal Neural Machine Translation model in which a doubly-attentive decoder naturally incorporates spatial visual features obtained using pre-trained convolutional neural networks, bridging the gap between image…

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates,…

Ultrasound images acquired from different devices exhibit diverse styles, resulting in decreased performance of downstream tasks. To mitigate the style gap, unpaired image-to-image (UI2I) translation methods aim to transfer images from a…

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting…

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches often rely on pretrained encoders, semantic distillation,…

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the…

Diadochokinetic speech tasks (DDK), in which participants repeatedly produce syllables, are commonly used as part of the assessment of speech motor impairments. These studies rely on manual analyses that are time-intensive, subjective, and…

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does…

This paper targets the perceptual task of separating the different interacting voices, i.e., monophonic melodic streams, in a polyphonic musical piece. We target symbolic music, where notes are explicitly encoded, and model this task as a…

DNN-based watermarking methods have rapidly advanced, with the ``Encoder-Noise Layer-Decoder'' (END) framework being the most widely used. To ensure end-to-end training, the noise layer in the framework must be differentiable. However,…

Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without…

Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving…

We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. Specifically, we update the model parameters with source- and target-side denoising tasks at the early stage and then tune…

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods. It's obvious that the quality of the semantic representations from encoding is very…

Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under…

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm.…

Conditional music generation offers significant advantages in terms of user convenience and control, presenting great potential in AI-generated content research. However, building conditional generative systems for multitrack popular songs…