English
Related papers

Related papers: Analysing the Language of Neural Audio Codecs

200 papers

Speech language models (LMs) are promising for high-quality speech synthesis through in-context learning. A typical speech LM takes discrete semantic units as content and a short utterance as prompt, and synthesizes speech which preserves…

Computation and Language · Computer Science 2024-03-20 Yifan Peng , Ilia Kulikov , Yilin Yang , Sravya Popuri , Hui Lu , Changhan Wang , Hongyu Gong

Speech codecs that convert continuous speech signals into discrete tokens have become essential for speech language models. However, existing codecs struggle to balance high-quality reconstruction with semantically rich representations,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-16 Wenxi Chen , Xinsheng Wang , Ruiqi Yan , Yushen Chen , Zhikang Niu , Ziyang Ma , Xiquan Li , Yuzhe Liang , Hanlin Wen , Shunshun Yin , Ming Tao , Xie Chen

Neural audio codecs (NACs) have garnered significant attention as key technologies for audio compression as well as audio representation for speech language models. While mainstream NAC models are predominantly convolution-based, the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-29 Haibin Wu , Naoyuki Kanda , Sefik Emre Eskimez , Jinyu Li

How much audio is needed to fully observe a multilingual ASR model's learned sub-token inventory across languages, and does data disparity in multilingual pre-training affect how these tokens are utilized during inference? We address this…

Computation and Language · Computer Science 2025-10-28 Siyu Liang , Nicolas Ballier , Gina-Anne Levow , Richard Wright

Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech codecs employ either acoustic features or learned blind…

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

The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and…

Sound · Computer Science 2022-10-07 Daniele Mari , Federica Latora , Simone Milani

The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba

Keywords in scientific articles have found their significance in information filtering and classification. In this article, we empirically investigated statistical characteristics and evolutionary properties of keywords in a very famous…

Data Analysis, Statistics and Probability · Physics 2009-06-23 Zike Zhang , Linyuan Lv , Jian-Guo Liu , Tao Zhou

n-tuple power law widely exists in language, computer program code, DNA and music. After a vast amount of Zipf analyses of n-tuple power law from empirical data, we propose a model to explain the n-tuple power law feature existed in these…

Data Analysis, Statistics and Probability · Physics 2009-08-05 Xiaocong Gan , Dahui Wang , Zhangang Han

In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Shengpeng Ji , Minghui Fang , Jialong Zuo , Ziyue Jiang , Dingdong Wang , Hanting Wang , Hai Huang , Zhou Zhao

The article introduces corrections to Zipf's and Heaps' laws based on systematic models of the proportion of hapaxes, i.e., words that occur once. The derivation rests on two assumptions: The first one is the standard urn model which…

Computation and Language · Computer Science 2025-05-27 Łukasz Dębowski

Neural Audio Codecs (NACs) have become increasingly adopted in speech processing tasks due to their excellent rate-distortion performance and compatibility with Large Language Models (LLMs) as discrete feature representations for audio…

Sound · Computer Science 2025-09-15 Harry Julian , Rachel Beeson , Lohith Konathala , Johanna Ulin , Jiameng Gao

Large language models (LLMs) commonly boost reasoning via sample-evaluate-ensemble decoders, achieving label free gains without ground truth. However, prevailing strategies score candidates using only external outputs such as token…

Computation and Language · Computer Science 2025-10-31 Kang Chen , Yaoning Wang , Kai Xiong , Zhuoka Feng , Wenhe Sun , Haotian Chen , Yixin Cao

With the rise of Speech Large Language Models (Speech LLMs), there has been growing interest in discrete speech tokens for their ability to integrate with text-based tokens seamlessly. Compared to most studies that focus on continuous…

Computation and Language · Computer Science 2024-11-14 Dingdong Wang , Mingyu Cui , Dongchao Yang , Xueyuan Chen , Helen Meng

Protecting speaker identity is crucial for online voice applications, yet streaming speaker anonymization (SA) remains underexplored. Recent research has demonstrated that neural audio codec (NAC) provides superior speaker feature…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-06 Nikita Kuzmin , Songting Liu , Kong Aik Lee , Eng Siong Chng

We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations…

Good speech quality has been achieved using waveform matching and parametric reconstruction coders. Recently developed very low bit rate generative codecs can reconstruct high quality wideband speech with bit streams less than 3 kb/s. These…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-23 Wissam A. Jassim , Jan Skoglund , Michael Chinen , Andrew Hines

Human language, as a typical complex system, its organization and evolution is an attractive topic for both physical and cultural researchers. In this paper, we present the first exhaustive analysis of the text organization of human speech.…

Computation and Language · Computer Science 2015-01-08 Ruokuang Lin , Qianli D. Y. Ma , Chunhua Bian

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-15 Shu-wen Yang , Byeonggeun Kim , Kuan-Po Huang , Qingming Tang , Huy Phan , Bo-Ru Lu , Harsha Sundar , Shalini Ghosh , Hung-yi Lee , Chieh-Chi Kao , Chao Wang

Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acoustic reconstruction, leaving emotion expressiveness…

Sound · Computer Science 2026-05-13 Jiacheng Shi , Hongfei Du , Xinyuan Song , Y. Alicia Hong , Yanfu Zhang , Ye Gao