English
Related papers

Related papers: Analysing the Language of Neural Audio Codecs

200 papers

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 speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao

A new class of audio deepfakes-codecfakes (CFs)-has recently caught attention, synthesized by Audio Language Models that leverage neural audio codecs (NACs) in the backend. In response, the community has introduced dedicated benchmarks and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-17 Orchid Chetia Phukan , Girish , Mohd Mujtaba Akhtar , Arun Balaji Buduru , Rajesh Sharma

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

We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional…

Sound · Computer Science 2024-07-29 Neil Shah , Shirish Karande , Vineet Gandhi

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Computation and Language · Computer Science 2025-10-30 Shreyas Gopal , Ashutosh Anshul , Haoyang Li , Yue Heng Yeo , Hexin Liu , Eng Siong Chng

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-17 Siyang Wang , Éva Székely

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

Objective speech-quality metrics are widely used to assess codec performance. However, for neural codecs, it is often unclear which metrics provide reliable quality estimates. To address this, we evaluated 45 objective metrics by…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-30 Wolfgang Mack , Nezih Topaloglu , Laura Lechler , Ivana Balić , Alexandra Craciun , Mansur Yesilbursa , Kamil Wojcicki

In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…

Computation and Language · Computer Science 2023-10-10 Robin Algayres , Yossi Adi , Tu Anh Nguyen , Jade Copet , Gabriel Synnaeve , Benoit Sagot , Emmanuel Dupoux

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Kai Zhen , Mi Suk Lee , Jongmo Sung , Seungkwon Beack , Minje Kim

It is widely accepted that information derived from analyzing speech (the acoustic signal) and language production (words and sentences) serves as a useful window into the health of an individual's cognitive ability. In fact, most…

Computation and Language · Computer Science 2019-11-06 Rohit Voleti , Julie M. Liss , Visar Berisha

Neural audio codecs have revolutionized audio processing by enabling speech tasks to be performed on highly compressed representations. Recent work has shown that speech separation can be achieved within these compressed domains, offering…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-28 Jia Qi Yip , Chin Yuen Kwok , Bin Ma , Eng Siong Chng

Second-order statistical methods show very good results for automatic speaker identification in controlled recording conditions. These approaches are generally used on the entire speech material available. In this paper, we study the…

Information Retrieval · Computer Science 2024-02-27 Ivan Magrin-Chagnolleau , Jean François Bonastre , Frédéric Bimbot

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-19 Edresson Casanova , Ryan Langman , Paarth Neekhara , Shehzeen Hussain , Jason Li , Subhankar Ghosh , Ante Jukić , Sang-gil Lee

We investigate the origin of Zipf's law for words in written texts by means of a stochastic dynamical model for text generation. The model incorporates both features related to the general structure of languages and memory effects inherent…

Statistical Mechanics · Physics 2007-05-23 Damián H. Zanette , Marcelo A. Montemurro

We introduce BANC, a neural binaural audio codec designed for efficient speech compression in single and two-speaker scenarios while preserving the spatial location information of each speaker. Our key contributions are as follows: 1) The…

Sound · Computer Science 2024-11-26 Anton Ratnarajah , Shi-Xiong Zhang , Dong Yu

While utilizing syntactic tools such as parts-of-speech (POS) tagging has helped us understand sentence structures and their distribution across diverse corpora, it is quite complex and poses a challenge in natural language processing…

Computation and Language · Computer Science 2025-12-15 Abhijeet Sahdev

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

In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE.…

Computation and Language · Computer Science 2019-01-28 Aran Komatsuzaki
‹ Prev 1 4 5 6 7 8 10 Next ›