相关论文: Music to Dance as Language Translation using Seque…

In the use of deep neural networks, it is crucial to provide appropriate input representations for the network to learn from. In this paper, we propose an approach to learn a representation that focus on rhythmic representation which is…

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant…

Learning a good distance measure for distance-based classification in time series leads to significant performance improvement in many tasks. Specifically, it is critical to effectively deal with variations and temporal dependencies in time…

Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…

Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between instruction following (i.e., follow open-ended…

This paper presents a generative AI model for automated music composition with LSTM networks that takes a novel approach at encoding musical information which is based on movement in music rather than absolute pitch. Melodies are encoded as…

Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various musical elements. These improvements primarily focused on…

Song translation requires both translation of lyrics and alignment of music notes so that the resulting verse can be sung to the accompanying melody, which is a challenging problem that has attracted some interests in different aspects of…

Although all-in-one-model multilingual neural machine translation (multilingual NMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignored, i.e., different language pairs reaching convergence in…

Training code-switched language models is difficult due to lack of data and complexity in the grammatical structure. Linguistic constraint theories have been used for decades to generate artificial code-switching sentences to cope with this…

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four…

Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by…

We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering…

Machine-learning techniques have been recently used with spectacular results to generate artefacts such as music or text. However, these techniques are still unable to capture and generate artefacts that are convincingly structured. In this…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning. However, due to the mixture of multilingual data during the pre-training of LLM, the…

The growing popularity of neural machine translation (NMT) and LLMs represented by ChatGPT underscores the need for a deeper understanding of their distinct characteristics and relationships. Such understanding is crucial for language…

Dance requires skillful composition of complex movements that follow rhythmic, tonal and timbral features of music. Formally, generating dance conditioned on a piece of music can be expressed as a problem of modelling a high-dimensional…

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ…

The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While cross-lingual transfer (XLT) methods have contributed to…