相关论文: High-Fidelity Audio Compression with Improved RVQG…

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments…

In this work, we study the task of Audio Language Modeling, in which we aim at learning probabilistic models for audio that can be used for generation and completion. We use a state-of-the-art perceptually-guided audio compression model, to…

A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that…

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy…

Perceptual quality of audio is the combination of aural accuracy and listener-perceived sound fidelity. It is how humans respond to the accuracy, intelligibility, and fidelity of aural media. Today this fidelity is also heavily influenced…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Deepfakes have become a universal and rapidly intensifying concern of generative AI across various media types such as images, audio, and videos. Among these, audio deepfakes have been of particular concern due to the ease of high-quality…

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source-filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch…

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational…

The advent of Large Models marks a new era in machine learning, significantly outperforming smaller models by leveraging vast datasets to capture and synthesize complex patterns. Despite these advancements, the exploration into scaling,…

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

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…