Related papers: Diffsound: Discrete Diffusion Model for Text-to-so…

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

This paper aims to apply a new deep learning approach to the task of generating raw audio files. It is based on diffusion models, a recent type of deep generative model. This new type of method has recently shown outstanding results with…

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…

Text-to-image diffusion models have demonstrated an impressive ability to produce high-quality outputs. However, they often struggle to accurately follow fine-grained spatial information in an input text. To this end, we propose a…

Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the…

Latent diffusion models have emerged as the dominant paradigm for many generation tasks including audio generation such as text-to-audio, text-to-music and text-to-speech. A key component of latent diffusion is an autoencoder (VAE) that…

Acoustic echo and background noise pose challenges on speech enhancement in hands-free systems and speakerphones. Discriminatively trained end-to-end methods represent a powerful solution for joint acoustic echo control (AEC) and denoising.…

While large language models have proven effective in a huge range of downstream applications, they often generate text that is problematic or lacks a desired attribute. In this paper, we introduce Reward-Augmented Decoding (RAD), a text…

Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a…

Generative models have attracted significant interest due to their ability to handle uncertainty by learning the inherent data distributions. However, two prominent generative models, namely Generative Adversarial Networks (GANs) and…

Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical…

Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting…

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma…

While most music generation models use textual or parametric conditioning (e.g. tempo, harmony, musical genre), we propose to condition a language model based music generation system with audio input. Our exploration involves two distinct…

We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each…

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly…

Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle…