Cover Image

A Comparative Study on Positional Encoding for Time-frequency Domain Dual-path Transformer-based Source Separation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Saijo, Kohei, Ogawa, Tetsuji
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Task-Aware Unified Source Separation
by: Saijo, Kohei, et al.
Published: (2024)

TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
by: Saijo, Kohei, et al.
Published: (2024)

Enhanced Reverberation as Supervision for Unsupervised Speech Separation
by: Saijo, Kohei, et al.
Published: (2024)

FasTUSS: Faster Task-Aware Unified Source Separation
by: Paissan, Francesco, et al.
Published: (2025)

An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement
by: Zhang, Qiquan, et al.
Published: (2024)

Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
by: Zhang, Wangyou, et al.
Published: (2024)

Subband Splitting: Simple, Efficient and Effective Technique for Solving Block Permutation Problem in Determined Blind Source Separation
by: Matsumoto, Kazuki, et al.
Published: (2024)

Input-Adaptive Spectral Feature Compression by Sequence Modeling for Source Separation
by: Saijo, Kohei, et al.
Published: (2026)

Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition
by: Higuchi, Yosuke, et al.
Published: (2023)

Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation
by: Saijo, Kohei, et al.
Published: (2025)

Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
by: Jiang, Xilin, et al.
Published: (2024)

Blind Source Separation of Radar Signals in Time Domain Using Deep Learning
by: Hinderer, Sven
Published: (2025)

FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement
by: Masuyama, Yoshiki, et al.
Published: (2025)

Determined Multichannel Blind Source Separation with Clustered Source Model
by: Wang, Jianyu, et al.
Published: (2024)

Leveraging Audio-Only Data for Text-Queried Target Sound Extraction
by: Saijo, Kohei, et al.
Published: (2024)

CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation
by: Kalkhorani, Vahid Ahmadi, et al.
Published: (2024)

MAPSS: Manifold-based Assessment of Perceptual Source Separation
by: Ivry, Amir, et al.
Published: (2025)

Efficient Area-based and Speaker-Agnostic Source Separation
by: Strauss, Martin, et al.
Published: (2024)

Janssen 2.0: Audio Inpainting in the Time-frequency Domain
by: Mokrý, Ondřej, et al.
Published: (2024)

MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
by: Zhao, Shengkui, et al.
Published: (2023)

Determined Blind Source Separation with Sinkhorn Divergence-based Optimal Allocation of the Source Power
by: Wang, Jianyu, et al.
Published: (2025)

Toward Universal Speech Enhancement for Diverse Input Conditions
by: Zhang, Wangyou, et al.
Published: (2023)

Source Separation by Flow Matching
by: Scheibler, Robin, et al.
Published: (2025)

SELEBI: Percussion-aware Time Stretching via Selective Magnitude Spectrogram Compression by Nonstationary Gabor Transform
by: Akaishi, Natsuki, et al.
Published: (2026)

Geneses: Unified Generative Speech Enhancement and Separation
by: Asai, Kohei, et al.
Published: (2026)

Reference Microphone Selection for Guided Source Separation based on the Normalized L-p Norm
by: Lohmann, Anselm, et al.
Published: (2025)

Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor
by: Lee, Younglo, et al.
Published: (2024)

Leveraging Sound Source Trajectories for Universal Sound Separation
by: Wu, Donghang, et al.
Published: (2024)

Improving Music Source Separation with Diffusion and Consistency Refinement
by: Karchkhadze, Tornike, et al.
Published: (2024)

Blind Source Separation in Biomedical Signals Using Variational Methods
by: Torabi, Yasaman, et al.
Published: (2025)

EDSep: An Effective Diffusion-Based Method for Speech Source Separation
by: Dong, Jinwei, et al.
Published: (2025)

Unsupervised Single-Channel Audio Separation with Diffusion Source Priors
by: Shi, Runwu, et al.
Published: (2025)

Exploiting Music Source Separation for Automatic Lyrics Transcription with Whisper
by: Syed, Jaza, et al.
Published: (2025)

Generating Piano Music with Transformers: A Comparative Study of Scale, Data, and Metrics
by: Lehmkuhl, Jonathan, et al.
Published: (2025)

Distribution Preserving Source Separation With Time Frequency Predictive Models
by: T., Pedro J. Villasana, et al.
Published: (2023)

URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement Competition
by: Wang, Jiahe, et al.
Published: (2025)

An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation
by: Vardhan, Saarth, et al.
Published: (2024)

ICASSP 2026 URGENT Speech Enhancement Challenge
by: Li, Chenda, et al.
Published: (2026)

Enhanced Automatic Drum Transcription via Drum Stem Source Separation
by: Riley, Xavier, et al.
Published: (2025)

Exploring Text-Queried Sound Event Detection with Audio Source Separation
by: Yin, Han, et al.
Published: (2024)