English
Related papers

Related papers: Exploring Token-Space Manipulation in Latent Audio…

200 papers

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Aniruddha Mahapatra , Long Mai , David Bourgin , Yitian Zhang , Feng Liu

Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio, however, often contains mixed speech and background sounds,…

Sound · Computer Science 2025-09-12 Xiaoxue Luo , Jinwei Huang , Runyan Yang , Yingying Gao , Junlan Feng , Chao Deng , Shilei Zhang

Discrete audio representation, aka audio tokenization, has seen renewed interest driven by its potential to facilitate the application of text language modeling approaches in audio domain. To this end, various compression and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-21 Krishna C. Puvvada , Nithin Rao Koluguri , Kunal Dhawan , Jagadeesh Balam , Boris Ginsburg

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-28 Arijit Biswas , Dai Jia

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Computation and Language · Computer Science 2026-01-14 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space. As a result, they are poorly robust to a global variation of the input…

Sound · Computer Science 2026-02-18 Samir Sadok , Laurent Girin , Xavier Alameda-Pineda

Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called…

Machine Learning · Computer Science 2020-01-23 Hanwei Wu , Markus Flierl

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

When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as…

Image and Video Processing · Electrical Eng. & Systems 2022-09-07 Saeed Ranjbar Alvar , Mateen Ulhaq , Hyomin Choi , Ivan V. Bajić

Lattices are compact representations that encode multiple hypotheses, such as speech recognition results or different word segmentations. It is shown that encoding lattices as opposed to 1-best results generated by automatic speech…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

Computation and Language · Computer Science 2026-03-11 Yen-Ju Lu , Yashesh Gaur , Wei Zhou , Benjamin Muller , Jesus Villalba , Najim Dehak , Luke Zettlemoyer , Gargi Ghosh , Mike Lewis , Srinivasan Iyer , Duc Le

Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and…

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

In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, existing models predominantly operate directly in the acoustic…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Zheqi Dai , Guangyan Zhang , Haolin He , Xiquan Li , Jingyu Li , Chunyat Wu , Yiwen Guo , Qiuqiang Kong

Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…

Sound · Computer Science 2024-06-18 Shoval Messica , Yossi Adi

In this paper, we focus on motion discrete tokenization, which converts raw motion into compact discrete tokens--a process proven crucial for efficient motion generation. In this paradigm, increasing the number of tokens is a common…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Sheng Yan , Yong Wang , Xin Du , Junsong Yuan , Mengyuan Liu

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

Computation and Language · Computer Science 2023-06-01 Jeremiah Milbauer , Annie Louis , Mohammad Javad Hosseini , Alex Fabrikant , Donald Metzler , Tal Schuster

Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…

Computation and Language · Computer Science 2024-10-08 Craig W. Schmidt , Varshini Reddy , Haoran Zhang , Alec Alameddine , Omri Uzan , Yuval Pinter , Chris Tanner

Variation in language is ubiquitous and often systematically linked to regional, social, and contextual factors. Tokenizers split texts into smaller units and might behave differently for less common linguistic forms. This might affect…

Computation and Language · Computer Science 2025-07-08 Anna Wegmann , Dong Nguyen , David Jurgens

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiawei Yang , Tianhong Li , Lijie Fan , Yonglong Tian , Yue Wang

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Sound · Computer Science 2026-03-12 Sofiene Kammoun , Xavier Alameda-Pineda , Simon Leglaive