Neural Information Processing Systems http://nips.cc/

These embeddings are decoded by a single four-layer convolutional network to generate notes from nearly 1000 instruments, 65 pitches per instrument on average and 5 velocities.

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging.

ABSTRACT Research on audio generation has progressively shifted from waveform-based approaches to spectrogram-based methods, which more naturally capture harmonic and temporal structures. At the same time, advances in image synthesis have shown that autoregression across scales, rather than tokens, improves coherence and detail. Building on these ideas, we introduce MARS (Multi-channel AutoRegression on Spectrograms), a framework that treats spectrograms as multi-channel images and employs channel multiplexing (CMX), a reshaping technique that lowers height and width without discarding information. A shared tokenizer provides consistent discrete representations across scales, enabling a transformer-based autoregressor to refine spectrograms from coarse to fine resolutions efficiently. Experiments on a large-scale dataset demonstrate that MARS performs comparably or better than state-of-the-art baselines across multiple evaluation metrics, establishing an efficient and scalable paradigm for high-fidelity audio generation. 1. INTRODUCTION In recent years, audio generation has undergone significant advancements, primarily fueled by the rapid development of deep generative models.

Despite the remarkable progress in the synthesis speed and fidelity of neural vocoders, their high energy consumption remains a critical barrier to practical deployment on computationally restricted edge devices. Spiking Neural Networks (SNNs), widely recognized for their high energy efficiency due to their event-driven nature, offer a promising solution for low-resource scenarios. In this paper, we propose Spiking Vocos, a novel spiking neural vocoder with ultra-low energy consumption, built upon the efficient Vocos framework. To mitigate the inherent information bottleneck in SNNs, we design a Spiking ConvNeXt module to reduce Multiply-Accumulate (MAC) operations and incorporate an amplitude shortcut path to preserve crucial signal dynamics. Furthermore, to bridge the performance gap with its Artificial Neural Network (ANN) counterpart, we introduce a self-architectural distillation strategy to effectively transfer knowledge. A lightweight Temporal Shift Module is also integrated to enhance the model's ability to fuse information across the temporal dimension with negligible computational overhead. Experiments demonstrate that our model achieves performance comparable to its ANN counterpart, with UTMOS and PESQ scores of 3.74 and 3.45 respectively, while consuming only 14.7% of the energy. The source code is available at https://github.com/pymaster17/Spiking-Vocos.

While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation of long audio signals at the sample level, which demands high temporal resolution. This results in significant computational costs for attention map generation and limits their ability to efficiently process both global and local information. Additionally, the sequential nature of sample generation in neural vocoders poses difficulties for real-time processing, making the direct adoption of transformers impractical. To address these challenges, we propose RingFormer, a neural vocoder that incorporates the ring attention mechanism into a lightweight transformer variant, the convolution-augmented transformer (Conformer). Ring attention effectively captures local details while integrating global information, making it well-suited for processing long sequences and enabling real-time audio generation. RingFormer is trained using adversarial training with two discriminators. The proposed model is applied to the decoder of the text-to-speech model VITS and compared with state-of-the-art vocoders such as HiFi-GAN, iSTFT-Net, and BigVGAN under identical conditions using various objective and subjective metrics. Experimental results show that RingFormer achieves comparable or superior performance to existing models, particularly excelling in real-time audio generation. Our code and audio samples are available on GitHub.

We present ZeroBAS, a neural method to synthesize binaural audio from monaural audio recordings and positional information without training on any binaural data. To our knowledge, this is the first published zero-shot neural approach to mono-to-binaural audio synthesis. Specifically, we show that a parameter-free geometric time warping and amplitude scaling based on source location suffices to get an initial binaural synthesis that can be refined by iteratively applying a pretrained denoising vocoder. Furthermore, we find this leads to generalization across room conditions, which we measure by introducing a new dataset, TUT Mono-to-Binaural, to evaluate state-of-the-art monaural-to-binaural synthesis methods on unseen conditions. Our zero-shot method is perceptually on-par with the performance of supervised methods on the standard mono-to-binaural dataset, and even surpasses them on our out-of-distribution TUT Mono-to-Binaural dataset. Our results highlight the potential of pretrained generative audio models and zero-shot learning to unlock robust binaural audio synthesis.

Latent diffusion models have shown promising results in audio generation, making notable advancements over traditional methods. However, their performance, while impressive with short audio clips, faces challenges when extended to longer audio sequences. These challenges are due to model's self-attention mechanism and training predominantly on 10-second clips, which complicates the extension to longer audio without adaptation. In response to these issues, we introduce a novel approach, LiteFocus that enhances the inference of existing audio latent diffusion models in long audio synthesis. Observed the attention pattern in self-attention, we employ a dual sparse form for attention calculation, designated as same-frequency focus and cross-frequency compensation, which curtails the attention computation under same-frequency constraints, while enhancing audio quality through cross-frequency refillment. LiteFocus demonstrates substantial reduction on inference time with diffusion-based TTA model by 1.99x in synthesizing 80-second audio clips while also obtaining improved audio quality.

Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterpretable parameters. We propose a text-to-audio generation method that leverages a virtual modular sound synthesizer with only 78 parameters. Synthesizers have long been used by skilled sound designers for media like music and film due to their flexibility and intuitive controls. Our method, CTAG, iteratively updates a synthesizer's parameters to produce high-quality audio renderings of text prompts that can be easily inspected and tweaked. Sounds produced this way are also more abstract, capturing essential conceptual features over fine-grained acoustic details, akin to how simple sketches can vividly convey visual concepts. Our results show how CTAG produces sounds that are distinctive, perceived as artistic, and yet similarly identifiable to recent neural audio synthesis models, positioning it as a valuable and complementary tool.

Generative adversarial network (GAN) models can synthesize highquality audio signals while ensuring fast sample generation. However, they are difficult to train and are prone to several issues including mode collapse and divergence. In this paper, we introduce SpecDiff-GAN, a neural vocoder based on HiFi-GAN, which was initially devised for speech synthesis from mel spectrogram. In our model, the training stability is enhanced by means of a forward diffusion process which consists in injecting noise from a Gaussian distribution to both real and fake samples before inputting them to the discriminator. We further improve the model by exploiting a spectrally-shaped noise distribution with the aim to make the discriminator's task more challenging. We then show the merits of our proposed model for speech and music synthesis on several datasets. Our experiments confirm that our model compares favorably in audio quality and efficiency compared to several baselines.