English
Related papers

Related papers: Kanade: A Simple Disentangled Tokenizer for Spoken…

200 papers

Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling.…

Computation and Language · Computer Science 2024-01-24 Xin Zhang , Dong Zhang , Shimin Li , Yaqian Zhou , Xipeng Qiu

Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-19 Anup Singh , Vipul Arora , Kris Demuynck

In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…

Machine Learning · Computer Science 2023-10-24 Kyle Hsu , Will Dorrell , James C. R. Whittington , Jiajun Wu , Chelsea Finn

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…

Recent advancements in audio language models have underscored the pivotal role of audio tokenization, which converts audio signals into discrete tokens, thereby facilitating the application of language model architectures to the audio…

Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations. It is a crucial component in generative tasks such as speech coding and large language models (LLM). However, most…

Sound · Computer Science 2025-07-01 Youqiang Zheng , Weiping Tu , Yueteng Kang , Jie Chen , Yike Zhang , Li Xiao , Yuhong Yang , Long Ma

Speech tokenizers serve as foundational components for speech language models, yet current designs exhibit several limitations, including: 1) dependence on multi-layer residual vector quantization structures or high frame rates, 2) reliance…

Sound · Computer Science 2025-08-26 Yuancheng Wang , Dekun Chen , Xueyao Zhang , Junan Zhang , Jiaqi Li , Zhizheng Wu

In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance. We study a set of nine…

Computation and Language · Computer Science 2021-06-03 Phillip Rust , Jonas Pfeiffer , Ivan Vulić , Sebastian Ruder , Iryna Gurevych

This paper presents LongCat-Audio-Codec, an audio tokenizer and detokenizer solution designed for industrial grade end-to-end speech large language models. By leveraging a decoupled model architecture and a multistage training strategy,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-20 Xiaohan Zhao , Hongyu Xiang , Shengze Ye , Song Li , Zhengkun Tian , Guanyu Chen , Ke Ding , Guanglu Wan

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

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…

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

Large Audio Language Models (LALMs) have emerged with strong performance across diverse audio understanding tasks and can be further enhanced by neural audio codecs. Transitioning from multi-layer residual vector quantizers to a…

Sound · Computer Science 2025-12-05 Jingyi Li , Zhiyuan Zhao , Zhisheng Zhang , Yunfei Liu , Lijian Lin , Ye Zhu , Jiahao Wu , Qiuqiang Kong , Yu Li

Speech denoising is a generally adopted and impactful task, appearing in many common and everyday-life use cases. Although there are very powerful methods published, most of those are too complex for deployment in everyday and low-resources…

Sound · Computer Science 2025-05-07 Diep Luong , Mikko Heikkinen , Konstantinos Drossos , Tuomas Virtanen

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-09 Michael Kuhlmann , Adrian Meise , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

Large language models have revolutionized natural language processing by leveraging self-supervised pretraining on vast textual data. Inspired by this success, researchers have investigated various compression-based speech tokenization…

Computation and Language · Computer Science 2025-05-22 Richard He Bai , Tatiana Likhomanenko , Ruixiang Zhang , Zijin Gu , Zakaria Aldeneh , Navdeep Jaitly

Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches struggle to achieve both simultaneously. To address this, we…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Amir Hussein , Sameer Khurana , Gordon Wichern , Francois G. Germain , Jonathan Le Roux

A text-to-speech (TTS) model typically factorizes speech attributes such as content, speaker and prosody into disentangled representations.Recent works aim to additionally model the acoustic conditions explicitly, in order to disentangle…

Humans often speak in a continuous manner which leads to coherent and consistent prosody properties across neighboring utterances. However, most state-of-the-art speech synthesis systems only consider the information within each sentence…

Sound · Computer Science 2023-05-19 Ya-Jie Zhang , Wei Song , Yanghao Yue , Zhengchen Zhang , Youzheng Wu , Xiaodong He

Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is…

Computation and Language · Computer Science 2026-04-15 Yuhan Song , Linhao Zhang , Chuhan Wu , Aiwei Liu , Wei Jia , Houfeng Wang , Xiao Zhou