English
Related papers

Related papers: Analysing the Language of Neural Audio Codecs

200 papers

Audio Large Language Models (Audio LLMs) have demonstrated strong capabilities in integrating speech perception with language understanding. However, whether their internal representations align with human neural dynamics during…

Sound · Computer Science 2026-02-04 Haoyun Yang , Xin Xiao , Jiang Zhong , Yu Tian , Dong Xiaohua , Yu Mao , Hao Wu , Kaiwen Wei

Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both generate and understand audio. However, preserving key…

Recent advancements in neural audio codec (NAC) unlock new potential in audio signal processing. Studies have increasingly explored leveraging the latent features of NAC for various speech signal processing tasks. This paper introduces the…

Sound · Computer Science 2024-09-17 Yuan Fang , Jinglin Bai , Jiajie Wang , Xueliang Zhang

Audio captioning quality metrics which are typically borrowed from the machine translation and image captioning areas measure the degree of overlap between predicted tokens and gold reference tokens. In this work, we consider a metric…

Multimedia · Computer Science 2023-03-06 Rehana Mahfuz , Yinyi Guo , Erik Visser

Neural audio codecs have gained recent popularity for their use in generative modeling as they offer high-fidelity audio reconstruction at low bitrates. While human listening studies remain the gold standard for assessing perceptual…

Sound · Computer Science 2025-11-26 Luca A. Lanzendörfer , Florian Grötschla

In this paper, we propose a personalized neural speech codec, envisioning that personalization can reduce the model complexity or improve perceptual speech quality. Despite the common usage of speech codecs where only a single talker is…

Sound · Computer Science 2024-04-02 Inseon Jang , Haici Yang , Wootaek Lim , Seungkwon Beack , Minje Kim

When following a sequence - such as reading a text or tracking a user's activity - one can measure how the "dictionary" of distinct elements (types) grows with the number of observations (tokens). When this growth follows a power law, it is…

Physics and Society · Physics 2026-04-21 Célestin Zimmerlin , Thomas Louail , Manuel Moussallam , Marc Barthelemy

With the rise of Speech Large Language Models (SpeechLLMs), two dominant approaches have emerged for speech processing: discrete tokens and continuous features. Each approach has demonstrated strong capabilities in audio-related processing…

Computation and Language · Computer Science 2025-08-26 Dingdong Wang , Junan Li , Mingyu Cui , Dongchao Yang , Xueyuan Chen , Helen Meng

Preserving speech intelligibility is a minimum requirement for speech codecs in communication. Recently, very low-bitrate neural codecs have gained interest for replacing classical codecs, reinforcing the need to evaluate whether…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-06 Lyonel Behringer , Anna Leschanowsky , Anjana Rajasekhar , Emily Kratsch , Guillaume Fuchs

Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-16 Patrick O'Reilly , Prem Seetharaman , Jiaqi Su , Zeyu Jin , Bryan Pardo

This paper investigates the temporal excitation patterns of creaky voice. Creaky voice is a voice quality frequently used as a phrase-boundary marker, but also as a means of portraying attitude, affective states and even social status.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-02 Thomas Drugman , John Kane , Christer Gobl

Linguistic laws constitute one of the quantitative cornerstones of modern cognitive sciences and have been routinely investigated in written corpora, or in the equivalent transcription of oral corpora. This means that inferences of…

Physics and Society · Physics 2016-10-11 Ivan Gonzalez Torre , Bartolo Luque , Lucas Lacasa , Jordi Luque , Antoni Hernandez-Fernandez

The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale,…

Sound · Computer Science 2024-09-19 Haohan Guo , Fenglong Xie , Dongchao Yang , Xixin Wu , Helen Meng

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm.…

Sound · Computer Science 2025-10-16 Xue Jiang , Xiulian Peng , Yuan Zhang , Yan Lu

Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…

Computation and Language · Computer Science 2025-06-06 Clara Meister , Tiago Pimentel , Gian Wiher , Ryan Cotterell

Audio and speech coding lack unified evaluation and open-source testing. Many candidate systems were evaluated on proprietary, non-reproducible, or small data, and machine learning-based codecs are often tested on datasets with similar…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-04 Jozef Coldenhoff , Niclas Granqvist , Milos Cernak

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…

Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to…

Sound · Computer Science 2025-05-22 Jingguang Tian , Haoqin Sun , Xinhui Hu , Xinkang Xu

Current audio language models are predominantly text-first, either extending pre-trained text LLM backbones or relying on semantic-only audio tokens, limiting general audio modeling. This paper presents a systematic empirical study of…

Language model based text-to-speech (TTS) models, like VALL-E, have gained attention for their outstanding in-context learning capability in zero-shot scenarios. Neural speech codec is a critical component of these models, which can convert…

Sound · Computer Science 2024-03-12 Yong Ren , Tao Wang , Jiangyan Yi , Le Xu , Jianhua Tao , Chuyuan Zhang , Junzuo Zhou
‹ Prev 1 3 4 5 6 7 10 Next ›