The creativity of classical music arises not only from composers who craft the musical sheets but also from performers who interpret the static notations with expressive nuances. This paper addresses the challenge of generating classical piano performances from scratch, aiming to emulate the dual roles of composer and pianist in the creative process. We introduce the Expressive Compound Word (ECP) representation, which effectively captures both the metrical structure and expressive nuances of classical performances. Building on this, we propose the Expressive Music Variational AutoEncoder (XMVAE), a model featuring two branches: a Vector Quantized Variational AutoEncoder (VQ-VAE) branch that generates score-related content, representing the Composer, and a vanilla VAE branch that produces expressive details, fulfilling the role of Pianist. These branches are jointly trained with similar Seq2Seq architectures, leveraging a multiscale encoder to capture beat-level contextual information and an orthogonal Transformer decoder for efficient compound tokens decoding. Both objective and subjective evaluations demonstrate that XMVAE generates classical performances with superior musical quality compared to state-of-the-art models. Furthermore, pretraining the Composer branch on extra musical score datasets contribute to a significant performance gain.

Representing symbolic music with compound tokens, where each token consists of several different sub-tokens representing a distinct musical feature or attribute, offers the advantage of reducing sequence length. While previous research has validated the efficacy of compound tokens in music sequence modeling, predicting all sub-tokens simultaneously can lead to suboptimal results as it may not fully capture the interdependencies between them. We introduce the Nested Music Transformer (NMT), an architecture tailored for decoding compound tokens autoregressively, similar to processing flattened tokens, but with low memory usage. The NMT consists of two transformers: the main decoder that models a sequence of compound tokens and the sub-decoder for modeling sub-tokens of each compound token. The experiment results showed that applying the NMT to compound tokens can enhance the performance in terms of better perplexity in processing various symbolic music datasets and discrete audio tokens from the MAESTRO dataset.

We present an effective method for fusing visual-and-language representations for several question answering tasks including visual question answering and visual entailment. In contrast to prior works that concatenate unimodal representations or use only cross-attention, we compose multimodal representations via channel fusion. By fusing on the channels, the model is able to more effectively align the tokens compared to standard methods. These multimodal representations, which we call compound tokens are generated with cross-attention transformer layers. First, vision tokens are used as queries to retrieve compatible text tokens through cross-attention. We then chain the vision tokens and the queried text tokens along the channel dimension. We call the resulting representations compound tokens. A second group of compound tokens are generated using an analogous process where the text tokens serve as queries to the cross-attention layer. We demonstrate the effectiveness of compound tokens using an encoder-decoder vision-language model trained end-to-end in the open-vocabulary setting. Compound Tokens achieve highly competitive performance across a range of question answering tasks including GQA, VQA2.0, and SNLI-VE.