English
Related papers

Related papers: High-Fidelity and Low-Latency Universal Neural Voc…

200 papers

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Machine Learning · Computer Science 2019-12-18 Fahimeh Bahmaninezhad , Shi-Xiong Zhang , Yong Xu , Meng Yu , John H. L. Hansen , Dong Yu

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

This paper proposes a novel approach that uses deep neural networks for classifying imagined speech, significantly increasing the classification accuracy. The proposed approach employs only the EEG channels over specific areas of the brain…

Neurons and Cognition · Quantitative Biology 2020-03-24 Jerrin Thomas Panachakel , A. G. Ramakrishnan , A. G. Ramakrishnan

Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-14 Zhuohuang Zhang , Takuya Yoshioka , Naoyuki Kanda , Zhuo Chen , Xiaofei Wang , Dongmei Wang , Sefik Emre Eskimez

Digital Pre-Distortion (DPD) enhances signal quality in wideband RF power amplifiers (PAs). As signal bandwidths expand in modern radio systems, DPD's energy consumption increasingly impacts overall system efficiency. Deep Neural Networks…

Signal Processing · Electrical Eng. & Systems 2024-04-25 Yizhuo Wu , Ang Li , Mohammadreza Beikmirza , Gagan Deep Singh , Qinyu Chen , Leo C. N. de Vreede , Morteza Alavi , Chang Gao

The performances of automatic speech recognition (ASR) systems degrade drastically under noisy conditions. Explicit distortion modelling (EDM), as a feature compensation step, is able to enhance ASR systems under such conditions by…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-02 Z. Guo , C. Chen , E. S. Chng

Ultra reliable low latency communications (URLLC) is a new service class introduced in 5G which is characterized by strict reliability $(1-10^{-5})$ and low latency requirements (1 ms). To meet these requisites, several strategies like…

Signal Processing · Electrical Eng. & Systems 2021-12-01 Christian Padilla , Ramin Hashemi , Nurul Huda Mahmood , Matti Latva-aho

Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Hyeonjun An , Sihyun Kim , Chaerim Lim , Hyunjoon Kim , Rathijit Sen , Sangmin Jung , Hyeonsoo Lee , Dongwook Kim , Takki Yu , Jinkyu Jeong , Youngsok Kim , Kwanghyun Park

Ultra-reliable low-latency communications (URLLC) operate with short packets, where finite-blocklength effects make near-maximum-likelihood (near-ML) decoding desirable but often too costly. This paper proposes a two-stage near-ML decoding…

Information Theory · Computer Science 2026-02-10 Yubeen Jo , Geon Choi , Yongjune Kim , Namyoon Lee

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-23 Jagabandhu Mishra , Amartya Chowdhury , S. R. Mahadeva Prasanna

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success…

Computation and Language · Computer Science 2022-04-29 Heng-Jui Chang , Shu-wen Yang , Hung-yi Lee

In discrete generative modeling, two dominant paradigms demonstrate divergent capabilities: Masked Diffusion Language Models (MDLM) excel at semantic understanding and zero-shot generalization, whereas Uniform-noise Diffusion Language…

Computation and Language · Computer Science 2026-02-03 Yue Liu , Yuzhong Zhao , Zheyong Xie , Qixiang Ye , Jianbin Jiao , Yao Hu , Shaosheng Cao , Yunfan Liu

True-time-delay (TTD) beamformers can produce wideband, squint-free beams in both analog and digital signal domains, unlike frequency-dependent FFT beams. Our previous work showed that TTD beamformers can be efficiently realized using the…

Machine Learning · Computer Science 2025-03-27 Hansaka Aluvihare , Sivakumar Sivasankar , Xianqi Li , Arjuna Madanayake , Sirani M. Perera

Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in different feature scales. To address this issue, we propose a…

Computation and Language · Computer Science 2021-08-18 Tianlong Kong , Shouyi Yin , Dawei Zhang , Wang Geng , Xin Wang , Dandan Song , Jinwen Huang , Huiyu Shi , Xiaorui Wang

Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor generalization performance when using limited training data.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-11 Shoukang Hu , Xurong Xie , Shansong Liu , Jianwei Yu , Zi Ye , Mengzhe Geng , Xunying Liu , Helen Meng

Location-based services (LBS) are witnessing a rise in popularity owing to their key features of delivering powerful and personalized digital experiences. The recent developments in wireless sensing techniques make the realization of…

Signal Processing · Electrical Eng. & Systems 2023-05-30 Osamah A. Abdullah , Hayder Al-Hraishawi , Symeon Chatzinotas

Nonlinear effects in high-speed optical fiber systems fundamentally limit channel capacity. While traditional Digital Backward Propagation (DBP) with adaptive filters addresses these effects, its computational complexity remains…

Signal Processing · Electrical Eng. & Systems 2025-06-11 Xinyu Xiao , Zhennan Zhou , Bin Dong , Dingjiong Ma , Li Zhou , Jie Sun

In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-07 Yichen Lu , Jiaqi Song , Chao-Han Huck Yang , Shinji Watanabe

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

Sound · Computer Science 2022-03-17 Andong Li , Chengshi Zheng , Ziyang Zhang , Xiaodong Li

High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications. Latent factor analysis (LFA) is a typical representation learning method that extracts useful yet latent knowledge from HiDS matrices…

Machine Learning · Computer Science 2022-04-19 Di Wu , Peng Zhang , Yi He , Xin Luo