相关论文: LL-SDR: Low-Latency Speech enhancement through Dis…

One challenge of integrating speech input with large language models (LLMs) stems from the discrepancy between the continuous nature of audio data and the discrete token-based paradigm of LLMs. To mitigate this gap, we propose a method for…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance…

Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech. However, these approaches often rely on complex…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Self-supervised learning (SSL) has become a core technique in speech processing, but the high dimensionality of its representations makes discretization essential for improving efficiency. However, existing discretization methods still…

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The proposed model is evaluated against several ablated versions of…

This paper focuses on leveraging deep representation learning (DRL) for speech enhancement (SE). In general, the performance of the deep neural network (DNN) is heavily dependent on the learning of data representation. However, the DRL's…

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a…

Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we…

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…

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared…

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data…

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete,…

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…

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…