English
Related papers

Related papers: Analyzing and Mitigating Inconsistency in Discrete…

200 papers

Current neural audio codecs typically use residual vector quantization (RVQ) to discretize speech signals. However, they often experience codebook collapse, which reduces the effective codebook size and leads to suboptimal performance. To…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-12 Rui-Chen Zheng , Hui-Peng Du , Xiao-Hang Jiang , Yang Ai , Zhen-Hua Ling

Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty…

Computation and Language · Computer Science 2026-04-13 Chen Shani , Yuval Reif , Nathan Roll , Dan Jurafsky , Ekaterina Shutova

Chord recognition systems typically comprise an acoustic model that predicts chords for each audio frame, and a temporal model that casts these predictions into labelled chord segments. However, temporal models have been shown to only…

Sound · Computer Science 2018-08-17 Filip Korzeniowski , Gerhard Widmer

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Yang Yang , Yunpeng Li , George Sung , Shao-Fu Shih , Craig Dooley , Alessio Centazzo , Ramanan Rajeswaran

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

Neurodivergent people frequently experience decreased sound tolerance, with estimates suggesting it affects 50-70% of this population. This heightened sensitivity can provoke reactions ranging from mild discomfort to severe distress,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-15 Alexander Popescu , Rosie Frost , Milos Cernak

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…

In recent years, speech enhancement (SE) has achieved impressive progress with the success of deep neural networks (DNNs). However, the DNN approach usually fails to generalize well to unseen environmental noise that is not included in the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-09 Haoyu Li , Junichi Yamagishi

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. Yet existing models of coherence focus on measuring individual aspects of coherence (lexical overlap,…

Computation and Language · Computer Science 2017-09-26 Jiwei Li , Dan Jurafsky

Recent advances in text-to-audio generation enable models to translate natural-language descriptions into diverse musical output. However, the robustness of these systems under semantically equivalent prompt variations remains largely…

Sound · Computer Science 2026-05-06 Jiahui Wu

Audio codec models are widely used in audio communication as a crucial technique for compressing audio into discrete representations. Nowadays, audio codec models are increasingly utilized in generation fields as intermediate…

Sound · Computer Science 2023-05-09 Dongchao Yang , Songxiang Liu , Rongjie Huang , Jinchuan Tian , Chao Weng , Yuexian Zou

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as…

Computation and Language · Computer Science 2023-08-14 Cal Peyser , Zhong Meng , Ke Hu , Rohit Prabhavalkar , Andrew Rosenberg , Tara N. Sainath , Michael Picheny , Kyunghyun Cho

Neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. Neural codecs trained considering only source coding tend…

Sound · Computer Science 2022-07-05 Huaying Xue , Xiulian Peng , Xue Jiang , Yan Lu

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-29 Sung-Lin Yeh , Wei Zhou , Gil Keren , Duc Le , Zhong Meng , Hao Tang , Jay Mahadeokar , Ozlem Kalinli , Alexandre Mourachko

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Ziqian Wang , Xinfa Zhu , Zihan Zhang , YuanJun Lv , Ning Jiang , Guoqing Zhao , Lei Xie

This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence…

Sound · Computer Science 2024-11-14 Rawad Melhem , Assef Jafar , Oumayma Al Dakkak

While diffusion and autoregressive (AR) models have significantly advanced generative modeling, they each present distinct limitations. AR models, which rely on causal attention, cannot exploit future context and suffer from slow generation…

Sound · Computer Science 2025-08-04 Yanqing Liu , Ruiqing Xue , Chong Zhang , Yufei Liu , Gang Wang , Bohan Li , Yao Qian , Lei He , Shujie Liu , Sheng Zhao

A multi-task learning framework is proposed for optimizing a single deep neural network (DNN) for joint noise reduction (NR) and hearing loss compensation (HLC). A distinct training objective is defined for each task, and the DNN predicts…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-24 Philippe Gonzalez , Vera Margrethe Frederiksen , Torsten Dau , Tobias May

Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with…

Computation and Language · Computer Science 2021-05-11 Anne Beyer , Sharid Loáiciga , David Schlangen