English
Related papers

Related papers: Say More with Less: Variable-Frame-Rate Speech Tok…

200 papers

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

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from…

Computation and Language · Computer Science 2025-06-18 Li-Wei Chen , Takuya Higuchi , Zakaria Aldeneh , Ahmed Hussen Abdelaziz , Alexander Rudnicky

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…

Computation and Language · Computer Science 2025-11-14 Yuhao Wang , Ziyang Cheng , Heyang Liu , Ronghua Wu , Qunshan Gu , Yanfeng Wang , Yu Wang

Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Jindong Li , Dario Zanca , Vincent Christlein , Tim Hamann , Jens Barth , Peter Kämpf , Björn Eskofier

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…

How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic \textit{information} in the modulation spectrum of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-24 Samik Sadhu , Hynek Hermansky

This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of…

Computation and Language · Computer Science 2025-04-22 Mario M. Kubek , Shiraj Pokharel , Thomas Böhme , Emma L. McDaniel , Herwig Unger , Armin R. Mikler

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Claudio Zito , Fabio Tesser , Mauro Nicolao , Piero Cosi

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-13 Ravi Shankar , Archana Venkataraman

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

Computation and Language · Computer Science 2021-12-30 Tong Zhang , Wei Ye , Baosong Yang , Long Zhang , Xingzhang Ren , Dayiheng Liu , Jinan Sun , Shikun Zhang , Haibo Zhang , Wen Zhao

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and…

Information Retrieval · Computer Science 2024-03-22 Qijiong Liu , Hengchang Hu , Jiahao Wu , Jieming Zhu , Min-Yen Kan , Xiao-Ming Wu

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Computation and Language · Computer Science 2022-11-01 Xianghu Yue , Junyi Ao , Xiaoxue Gao , Haizhou Li

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Computation and Language · Computer Science 2025-05-20 Xianglong Xu , John Bowen , Rojin Taheri

When using an LLM to process text outside the training domain(s), an often overlooked factor is vocabulary mismatch, where the general-domain tokenizer fails to capture frequent domain-specific terms, leading to higher token fertility and…

Computation and Language · Computer Science 2025-10-01 Christian Herold , Michael Kozielski , Nicholas Santavas , Yannick Versley , Shahram Khadivi

In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-12 Mateusz Czyżnikiewicz , Łukasz Bondaruk , Jakub Kubiak , Adam Wiącek , Łukasz Degórski , Marek Kubis , Paweł Skórzewski

Effective human behavior modeling is critical for successful human-robot interaction. Current state-of-the-art approaches for predicting listening head behavior during dyadic conversations employ continuous-to-discrete representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Tri Tung Nguyen Nguyen , Quang Tien Dam , Dinh Tuan Tran , Joo-Ho Lee

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinying Lin , Xuyang Liu , Yiyu Wang , Teng Ma , Wenqi Ren