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

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…

Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…

Generative modeling has recently achieved remarkable success across text, image, and audio domains, demonstrating powerful capabilities for unified representation learning. However, audio generation models still face challenges in terms of…

Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization, which preserves reconstruction quality but complicates language modeling after sequence…

The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressive paradigm of large language models. A vision tokenizer trained for reconstruction excels at…

Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities. Unlike typical (non-streaming) voice conversion, which can leverage the entire…

Speech tokenizers are foundational to speech language models, yet existing approaches face two major challenges: (1) balancing trade-offs between encoding semantics for understanding and acoustics for reconstruction, and (2) achieving low…

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse…

We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By employing an InfoGAN-style objective, where we train a…

Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements…

The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarking provides a viable protection mechanism by embedding…

We propose a generative framework for multi-track music source separation (MSS) that reformulates the task as conditional discrete token generation. Unlike conventional approaches that directly estimate continuous signals in the time or…

Recent progress in natural language processing has been adapted to the symbolic music modality. Language models, such as Transformers, have been used with symbolic music for a variety of tasks among which music generation, modeling or…

Discrete representation learning has shown promising results across various domains, including generation and understanding in image, speech and language. Inspired by these advances, we propose MuseTok, a tokenization method for symbolic…

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in…

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…

Large Audio Language Models (LALMs) have emerged with strong performance across diverse audio understanding tasks and can be further enhanced by neural audio codecs. Transitioning from multi-layer residual vector quantizers to a…

Voice conversion is becoming increasingly popular, and a growing number of application scenarios require models with streaming inference capabilities. The recently proposed DualVC attempts to achieve this objective through streaming model…

Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides the denoising process from Gaussian noise to the target image…

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens…