English
Related papers

Related papers: MelTok: 2D Tokenization for Single-Codebook Audio …

200 papers

With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-21 Xiaoyu Yang , Qiujia Li , Chao Zhang , Phil Woodland

Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened…

Sound · Computer Science 2024-06-26 Jizhong Liu , Gang Li , Junbo Zhang , Heinrich Dinkel , Yongqing Wang , Zhiyong Yan , Yujun Wang , Bin Wang

Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into…

Sound · Computer Science 2024-10-22 Peiji Yang , Fengping Wang , Yicheng Zhong , Huawei Wei , Zhisheng Wang

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Xinliang Zhang , Lei Zhu , Hangzhou He , Shuang Zeng , Ourui Fu , Jiakui Hu , Zhengjian Yao , Yanye Lu

Speech Language Models (SpeechLMs) model tokenized speech to capture both semantic and acoustic information. When neural audio codecs based on Residual Vector Quantization (RVQ) are used as audio tokenizers, they produce multiple discrete…

Computation and Language · Computer Science 2026-03-06 Issa Sugiura , Shuhei Kurita , Yusuke Oda , Ryuichiro Higashinaka

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by this success, researchers have explored adapting these methods to speech by discretizing continuous…

Machine Learning · Computer Science 2025-10-28 Luca Della Libera , Francesco Paissan , Cem Subakan , Mirco Ravanelli

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,…

Machine Learning · Computer Science 2026-02-05 Luca Della Libera , Cem Subakan , Mirco Ravanelli

Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…

Computation and Language · Computer Science 2025-11-14 Yuhao Wang , Ziyang Cheng , Heyang Liu , Ronghua Wu , Qunshan Gu , Yanfeng Wang , Yu Wang

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Qihang Yu , Mark Weber , Xueqing Deng , Xiaohui Shen , Daniel Cremers , Liang-Chieh Chen

Neural audio codecs form the foundational building blocks for language model (LM)-based speech generation. Typically, there is a trade-off between frame rate and audio quality. This study introduces a low-frame-rate, semantically enhanced…

Sound · Computer Science 2025-10-02 Jiaqi Li , Xiaolong Lin , Zhekai Li , Shixi Huang , Yuancheng Wang , Chaoren Wang , Zhenpeng Zhan , Zhizheng Wu

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jusheng Zhang , Xiaoyang Guo , Kaitong Cai , Qinhan Lv , Yijia Fan , Wenhao Chai , Jian Wang , Keze Wang

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Sound · Computer Science 2025-12-29 Liuyang Bai , Weiyi Lu , Li Guo

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Anni Tang , Tianyu He , Junliang Guo , Xinle Cheng , Li Song , Jiang Bian

Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitation is that most are trained to maximize reconstruction…

Sound · Computer Science 2025-09-10 Dimitrios Bralios , Jonah Casebeer , Paris Smaragdis

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Junhao Du , Jialong Xue , Anqi Li , Jincheng Dai , Guo Lu

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Computation and Language · Computer Science 2026-05-14 Chong Li , Yingzhuo Deng , Wen Yang , Jiajun Zhang , Chengqing Zong

Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influences text-only LMs' ability to represent phonological knowledge. Through a series of…

Computation and Language · Computer Science 2026-04-21 Disen Liao , Freda Shi

Previous studies in automated audio captioning have faced difficulties in accurately capturing the complete temporal details of acoustic scenes and events within long audio sequences. This paper presents AudioLog, a large language models…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-05 Jisheng Bai , Han Yin , Mou Wang , Dongyuan Shi , Woon-Seng Gan , Jianfeng Chen , Susanto Rahardja

Speech tokenizers are a key building block of fully discrete Speech LLMs.Existing tokenizers either prioritize semantic encoding,fuse semantic content with acoustic style inseparably,or achieve incomplete semantic-acoustic…

Sound · Computer Science 2026-05-28 Hanlin Zhang , Daxin Tan , Dehua Tao , Xiao Chen , Haochen Tan , Yunhe Li , Yuchen Cao , Linqi Song