English
Related papers

Related papers: Segment Length Matters: A Study of Segment Lengths…

200 papers

Audio-Visual Segmentation (AVS) aims to produce pixel-level masks of sound producing objects in videos, by jointly learning from audio and visual signals. However, real-world environments are inherently dynamic, causing audio and visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Siddeshwar Raghavan , Gautham Vinod , Bruce Coburn , Fengqing Zhu

A novel approach for speech segmentation is proposed, based on Multilevel Hybrid (mean/min) Filters (MHF) with the following features: An accurate transition location. Good performance in noisy environments (gaussian and impulsive noise).…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-04 Marcos Faundez-Zanuy , Francesc Vallverdu-Bayes

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-11 Chenda Li , Lei Yang , Weiqin Wang , Yanmin Qian

We learn a discriminative fixed length feature representation of fingerprints which stands in contrast to commonly used unordered, variable length sets of minutiae points. To arrive at this fixed length representation, we embed fingerprint…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Joshua J. Engelsma , Kai Cao , Anil K. Jain

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable…

Computation and Language · Computer Science 2022-10-27 Albert Zeyer , Robin Schmitt , Wei Zhou , Ralf Schlüter , Hermann Ney

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally…

Computation and Language · Computer Science 2021-04-16 Yangming Li , Lemao Liu , Kaisheng Yao

The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real…

Sound · Computer Science 2025-09-24 Aditya Bhattacharjee , Marco Pasini , Emmanouil Benetos

More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage,…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-02 Qingjian Lin , Ruiqing Yin , Ming Li , Hervé Bredin , Claude Barras

Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples…

Databases · Computer Science 2016-09-28 Shahriar Shariat , Vladimir Pavlovic

We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module…

Computation and Language · Computer Science 2016-10-26 Yossi Adi , Joseph Keshet , Emily Cibelli , Matthew Goldrick

While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-27 Mingchen Shao , Hang Su , Wenjie Tian , Bingshen Mu , Zhennan Lin , Lichun Fan , Zhenbo Luo , Jian Luan , Lei Xie

For the task of speech recognition, the use of more than 30 seconds of acoustic context during training is uncommon and under-investigated in literature. In this work, we conduct an empirical study on the effect of scaling the sequence…

Computation and Language · Computer Science 2024-06-18 Robert Flynn , Anton Ragni

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

Computation and Language · Computer Science 2025-06-03 Shunsuke Kando , Yusuke Miyao , Shinnosuke Takamichi

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

Sound · Computer Science 2022-10-31 Sergey Novoselov , Vladimir Volokhov , Galina Lavrentyeva

Audio fingerprinting, exemplified by pioneers like Shazam, has transformed digital audio recognition. However, existing systems struggle with accuracy in challenging conditions, limiting broad applicability. This research proposes an AI and…

How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in…

The Audio-Visual Segmentation (AVS) task aims to segment sounding objects in the visual space using audio cues. However, in this work, it is recognized that previous AVS methods show a heavy reliance on detrimental segmentation preferences…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yaoting Wang , Peiwen Sun , Yuanchao Li , Honggang Zhang , Di Hu

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-12 Ilya Sklyar , Anna Piunova , Christian Osendorfer

We propose a method that quantifies the importance, namely relevance, of audio segments for classification in weakly-labelled problems. It works by drawing information from a set of class-wise one-vs-all classifiers. By selecting the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-13 Juliano Henrique Foleiss , Tiago Fernandes Tavares

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have observed a lot of renewed interest, including the extended…

Sound · Computer Science 2025-08-20 Sarthak Yadav , Sergios Theodoridis , Zheng-Hua Tan