相关论文: DeCodec: Rethinking Audio Codecs as Universal Dise…

Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space. As a result, they are poorly robust to a global variation of the input…

Human voice encodes both identity and paralinguistic cues, yet encoders in large audio-language models (LALMs) rarely balance both aspects. In this work, we present a study toward building a general-purpose voice encoder that captures…

A long-standing goal in the field of sensory substitution is to enable sound perception for deaf and hard of hearing (DHH) people by visualizing audio content. Different from existing models that translate to hand sign language, between…

Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete…

Brain-computer interfaces (BCI) offer numerous human-centered application possibilities, particularly affecting people with neurological disorders. Text or speech decoding from brain activities is a relevant domain that could augment the…

While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative…

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

Universal language representation is the holy grail in machine translation (MT). Thanks to the new neural MT approach, it seems that there are good perspectives towards this goal. In this paper, we propose a new architecture based on…

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

Neurophysiological recordings such as electroencephalography (EEG) offer accessible and minimally invasive means of estimating physiological activity for applications in healthcare, diagnostic screening, and even immersive entertainment.…

We present an open-source implementation of the Descript Audio Codec (DAC) using Google's JAX ecosystem of Flax, Optax, Orbax, AUX, and CLU. Our codebase enables the reuse of model weights from the original PyTorch DAC, and we confirm that…

We introduce LMCodec, a causal neural speech codec that provides high quality audio at very low bitrates. The backbone of the system is a causal convolutional codec that encodes audio into a hierarchy of coarse-to-fine tokens using residual…

Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation. Its interest has recently been demonstrated in computer…

Audio codecs are a critical component of modern speech generation systems. This paper introduces a low-bitrate, multi-scale residual codec that encodes speech into four distinct streams: semantic, timbre, prosody, and residual. This…

Sound field decomposition predicts waveforms in arbitrary directions using signals from a limited number of microphones as inputs. Sound field decomposition is fundamental to downstream tasks, including source localization, source…

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…

In real-world scenarios, speech signals are inevitably corrupted by various types of interference, making speech enhancement (SE) a critical task for robust speech processing. However, most existing SE methods only handle a limited range of…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates,…