English
Related papers

Related papers: Robust Phonetic Segmentation Using Spectral Transi…

200 papers

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Signal Processing · Electrical Eng. & Systems 2020-11-11 Xiaofei Li , Simon Leglaive , Laurent Girin , Radu Horaud

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-05 Bin Liu , Shuai Nie , Yaping Zhang , Shan Liang , Wenju Liu

This letter proposes a new time domain absorption approach designed to reduce masking components of speech signals under noisy-reverberant conditions. In this method, the non-stationarity of corrupted signal segments is used to detect…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-19 G. Zucatelli , R. Coelho

Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of large foundation models in novel scenarios with limited training data. In the computer vision community, PEFT has shown effectiveness in image…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Zelin Peng , Zhengqin Xu , Zhilin Zeng , Lingxi Xie , Qi Tian , Wei Shen

The Relative Transfer Matrix (ReTM), recently introduced as a generalization of the relative transfer function for multiple receivers and sources, shows promising performance when applied to speech enhancement and speaker separation in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-23 Wageesha N. Manamperi , Thushara D. Abhayapala

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Sound · Computer Science 2021-06-22 Mohammed Salah Al-Radhi , Tamás Gábor Csapó , Géza Németh

Cochlear implant (CI) users have considerable difficulty in understanding speech in reverberant listening environments. Time-frequency (T-F) masking is a common technique that aims to improve speech intelligibility by multiplying…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-01 Kevin M. Chu , Leslie M. Collins , Boyla O. Mainsah

Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM through prompting often overlook the domain shift issue,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Hui-Yue Yang , Hui Chen , Ao Wang , Kai Chen , Zijia Lin , Yongliang Tang , Pengcheng Gao , Yuming Quan , Jungong Han , Guiguang Ding

With continuing improvements on the quality of fabricated quantum devices, it becomes increasingly crucial to analyze noisy quantum process in greater details such as characterizing the non-Markovianity in a quantitative manner. In this…

Quantum Physics · Physics 2020-12-21 Yu-Qin Chen , Yi-Cong Zheng , Shengyu Zhang , Chang-Yu Hsieh

Single-microphone, speaker-independent speech separation is normally performed through two steps: (i) separating the specific speech sources, and (ii) determining the best output-label assignment to find the separation error. The second…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-07 Midia Yousefi , Soheil Khorram , John H. L. Hansen

Long Short-Term Memory (LSTM) is the primary recurrent neural networks architecture for acoustic modeling in automatic speech recognition systems. Residual learning is an efficient method to help neural networks converge easier and faster.…

Computation and Language · Computer Science 2017-08-21 Lu Huang , Jiasong Sun , Ji Xu , Yi Yang

Post-selection strategies have been proposed with the aim of amplifying weak signals, which may help to overcome detection thresholds associated with technical noise in high-precision measurements. Here we use an optical setup to…

Quantum Physics · Physics 2017-01-11 G. Bié Alves , A. Pimentel , M. Hor-Meyll , S. P. Walborn , L. Davidovich , R. L. de Matos Filho

Recent advances in machine learning and the availability of articulatory datasets allow vocal tract synthesis to be conditioned on phonetic sequences, a primary task of articulatory speech synthesis. However, quality assessment needs a…

Computation and Language · Computer Science 2026-05-21 Vinicius Ribeiro , Yves Laprie

Semantic segmentation is a critical task in computer vision aiming to identify and classify individual pixels in an image, with numerous applications in for example autonomous driving and medical image analysis. However, semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Halil Ibrahim Aysel , Xiaohao Cai , Adam Prügel-Bennett

Ground segmentation is crucial for terrestrial mobile platforms to perform navigation or neighboring object recognition. Unfortunately, the ground is not flat, as it features steep slopes; bumpy roads; or objects, such as curbs, flower…

Robotics · Computer Science 2022-03-11 Hyungtae Lim , Minho Oh , Hyun Myung

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in…

Computation and Language · Computer Science 2018-11-06 Julia Kreutzer , Artem Sokolov

Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical…

Computation and Language · Computer Science 2020-11-13 Sanket Shah , Satarupa Guha , Simran Khanuja , Sunayana Sitaram

Self-supervised representations of speech are currently being widely used for a large number of applications. Recently, some efforts have been made in trying to analyze the type of information present in each of these representations. Most…

Sound · Computer Science 2023-09-22 Pablo Riera , Manuela Cerdeiro , Leonardo Pepino , Luciana Ferrer

Maximum Voiced Frequency (MVF) is used in various speech models as the spectral boundary separating periodic and aperiodic components during the production of voiced sounds. Recent studies have shown that its proper estimation and modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-02 Thomas Drugman , Yannis Stylianou

Audio fingerprinting provides an identifiable representation of acoustic signals, which can be later used for identification and retrieval systems. To obtain a discriminative representation, the input audio is usually segmented into shorter…

‹ Prev 1 4 5 6 7 8 10 Next ›