English
Related papers

Related papers: ALMTokenizer: A Low-bitrate and Semantic-rich Audi…

200 papers

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we…

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

We study two foundational problems in audio language models: (1) how to design an audio tokenizer that can serve as an intermediate representation for both understanding and generation; and (2) how to build an audio foundation model that…

Sound · Computer Science 2026-02-12 Dongchao Yang , Yuanyuan Wang , Dading Chong , Songxiang Liu , Xixin Wu , Helen Meng

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…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Ziqian Wang , Xinfa Zhu , Zihan Zhang , YuanJun Lv , Ning Jiang , Guoqing Zhao , Lei Xie

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

Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-31 Alexander H. Liu , Qirui Wang , Yuan Gong , James Glass

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

Neural audio codecs have recently gained traction for their ability to compress high-fidelity audio and provide discrete tokens for generative modeling. However, leading approaches often rely on resource-intensive models and complex…

Sound · Computer Science 2025-08-18 Linwei Zhai , Han Ding , Cui Zhao , fei wang , Ge Wang , Wang Zhi , Wei Xi

In this paper, we propose SemanticAC, a semantics-assisted framework for Audio Classification to better leverage the semantic information. Unlike conventional audio classification methods that treat class labels as discrete vectors, we…

Sound · Computer Science 2023-02-14 Yicheng Xiao , Yue Ma , Shuyan Li , Hantao Zhou , Ran Liao , Xiu Li

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Computation and Language · Computer Science 2025-08-22 Dong Liu , Yanxuan Yu

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…

Sound · Computer Science 2026-04-21 Ho-Lam Chung , Yiming Chen , Hung-yi Lee

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…

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

Machine Learning · Computer Science 2019-07-03 Chien-Feng Liao , Yu Tsao , Xugang Lu , Hisashi Kawai

Automated Audio Captioning (AAC) aims to describe the semantic contexts of general sounds, including acoustic events and scenes, by leveraging effective acoustic features. To enhance performance, an AAC method, EnCLAP, employed discrete…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Daiki Takeuchi , Binh Thien Nguyen , Masahiro Yasuda , Yasunori Ohishi , Daisuke Niizumi , Noboru Harada

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…

Computation and Language · Computer Science 2024-06-21 Abul Hasan , Jinge Wu , Quang Ngoc Nguyen , Salomé Andres , Imane Guellil , Huayu Zhang , Arlene Casey , Beatrice Alex , Bruce Guthrie , Honghan Wu

We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation…

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which train acoustic tokenizers and subsequently integrate frozen…

A good language model starts with a good tokenizer. Tokenization is especially important for speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A speech tokenizer should extract…

Computation and Language · Computer Science 2026-05-06 Zhijie Huang , Stephen McIntosh , Daisuke Saito , Nobuaki Minematsu

Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel speech tokenizer with broad applicability across downstream…

Machine Learning · Computer Science 2025-07-10 Wonjin Jung , Sungil Kang , Dong-Yeon Cho

Discrete Audio codecs (or audio tokenizers) have recently regained interest due to the ability of Large Language Models (LLMs) to learn their compressed acoustic representations. Various publicly available trainable discrete tokenizers…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-14 Slava Shechtman , Avihu Dekel