English
Related papers

Related papers: Efficient Vocal Source Separation Through Windowed…

200 papers

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while…

Computation and Language · Computer Science 2025-12-11 Maximo Eduardo Rulli , Simone Petruzzi , Edoardo Michielon , Fabrizio Silvestri , Simone Scardapane , Alessio Devoto

The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Yunfeng Wu , Jiayi Song , Zhenxiong Tan , Zihao He , Songhua Liu

Speaker diarization has been mainly developed based on the clustering of speaker embeddings. However, the clustering-based approach has two major problems; i.e., (i) it is not optimized to minimize diarization errors directly, and (ii) it…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-16 Yusuke Fujita , Naoyuki Kanda , Shota Horiguchi , Yawen Xue , Kenji Nagamatsu , Shinji Watanabe

Audiovisual active speaker detection (ASD) in egocentric recordings is challenged by frequent occlusions, motion blur, and audio interference, which undermine the discernability of temporal synchrony between lip movement and speech.…

Multimedia · Computer Science 2025-08-15 Jason Clarke , Yoshihiko Gotoh , Stefan Goetze

In this paper we present a new method for text-independent speaker verification that combines segmental dynamic time warping (SDTW) and the d-vector approach. The d-vectors, generated from a feed forward deep neural network trained to…

Sound · Computer Science 2018-06-27 Mohamed Adel , Mohamed Afify , Akram Gaballah

Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Belen Alastruey , Lukas Drude , Jahn Heymann , Simon Wiesler

The increasing number of microphone-equipped personal devices offers great flexibility and potential using them as ad-hoc microphone arrays in dynamic meeting environments. However, most existing approaches are designed for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-23 Gene-Ping Yang , Sebastian Braun

We introduce a simple and linear SNR (strictly speaking, periodic to random power ratio) estimator (0dB to 80dB without additional calibration/linearization) for providing reliable descriptions of aperiodicity in speech corpus. The main…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-06 Hideki Kawahara , Ken-Ichi Sakakibara , Masanori Morise , Hideki Banno , Tomoki Toda

Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions,…

Sound · Computer Science 2020-12-01 Peng Zhang , Jiaming Xu , Jing shi , Yunzhe Hao , Bo Xu

Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation…

Sound · Computer Science 2022-11-01 Wooseok Shin , Hyun Joon Park , Jin Sob Kim , Byung Hoon Lee , Sung Won Han

The Swin transformer has recently attracted attention in medical image analysis due to its computational efficiency and long-range modeling capability. Owing to these properties, the Swin Transformer is suitable for establishing more…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Mingrui Ma , Tao Wang , Lei Song , Weijie Wang , Guixia Liu

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-30 Jee-weon Jung , You Jin Kim , Hee-Soo Heo , Bong-Jin Lee , Youngki Kwon , Joon Son Chung

Speaker verification (SV) aims to determine whether the speaker's identity of a test utterance is the same as the reference speech. In the past few years, extracting speaker embeddings using deep neural networks for SV systems has gone…

Sound · Computer Science 2022-05-27 Nan Zhang , Jianzong Wang , Zhenhou Hong , Chendong Zhao , Xiaoyang Qu , Jing Xiao

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in…

Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e.g., SwinIR) can significantly improve the model performance. Still, the computation overhead is also considerable when the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Yupeng Zhou , Zhen Li , Chun-Le Guo , Li Liu , Ming-Ming Cheng , Qibin Hou

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

We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT), augmented by input-dependent gating.…

Machine Learning · Computer Science 2026-04-13 Dipan Maity , Suman Mondal , Arindam Roy

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

Image and Video Processing · Electrical Eng. & Systems 2023-08-09 Rahul G. S. , Sriprabha Ramnarayanan , Mohammad Al Fahim , Keerthi Ram , Preejith S. P , Mohanasankar Sivaprakasam

In recent years, the integration of pre-trained foundational models with multiple instance learning (MIL) has improved diagnostic accuracy in computational pathology. However, existing MIL methods focus on optimizing feature extractors and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Le Feng , Li Xiao

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

Sound · Computer Science 2021-09-03 Jianwei Zhang , Suren Jayasuriya , Visar Berisha