Cover Image

Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luong, Diep, Heikkinen, Mikko, Drossos, Konstantinos, Virtanen, Tuomas
Format:	Preprint
Published:	2025
Subjects:	Sound Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Automatic Contextual Audio Denoising
by: Luong, Diep, et al.
Published: (2026)

Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays
by: Heikkinen, Mikko, et al.
Published: (2025)

Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
by: Drossos, Konstantinos, et al.
Published: (2025)

Adversarial Representation Learning for Robust Privacy Preservation in Audio
by: Gharib, Shayan, et al.
Published: (2023)

Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
by: Luong, Diep, et al.
Published: (2023)

Multi-Utterance Speech Separation and Association Trained on Short Segments
by: Wang, Yuzhu, et al.
Published: (2025)

Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers
by: Wang, Yuzhu, et al.
Published: (2025)

Neural Ambisonics encoding for compact irregular microphone arrays
by: Heikkinen, Mikko, et al.
Published: (2024)

Beyond Omnidirectional: Neural Ambisonics Encoding for Arbitrary Microphone Directivity Patterns using Cross-Attention
by: Heikkinen, Mikko, et al.
Published: (2026)

Moving Speaker Separation via Parallel Spectral-Spatial Processing
by: Wang, Yuzhu, et al.
Published: (2026)

Multi-Channel Replay Speech Detection using Acoustic Maps
by: Neri, Michael, et al.
Published: (2026)

Discriminating real and synthetic super-resolved audio samples using embedding-based classifiers
by: Silaev, Mikhail, et al.
Published: (2026)

From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning
by: Martinsson, John, et al.
Published: (2024)

Multi-label Zero-Shot Audio Classification with Temporal Attention
by: Dogan, Duygu, et al.
Published: (2024)

Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection
by: Zhang, Shiqi, et al.
Published: (2025)

Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music
by: Tunturi, Eetu, et al.
Published: (2025)

Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities
by: Sudarsanam, Parthasaarathy, et al.
Published: (2025)

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
by: Dai, Wang, et al.
Published: (2025)

Cosine Scoring with Uncertainty for Neural Speaker Embedding
by: Wang, Qiongqiong, et al.
Published: (2024)

MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
by: Jiang, Ziyue, et al.
Published: (2025)

Are Deep Speech Denoising Models Robust to Adversarial Noise?
by: Schwarzer, Will, et al.
Published: (2025)

Speaker Distance Estimation in Enclosures from Single-Channel Audio
by: Neri, Michael, et al.
Published: (2024)

SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
by: Garcia-Martinez, Jaime, et al.
Published: (2024)

Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications
by: Diaz-Guerra, David, et al.
Published: (2023)

Latent-Domain Predictive Neural Speech Coding
by: Jiang, Xue, et al.
Published: (2022)

Acoustic Simulation Framework for Multi-channel Replay Speech Detection
by: Neri, Michael, et al.
Published: (2025)

Learning Disentangled Speech Representations
by: Brima, Yusuf, et al.
Published: (2023)

RepCodec: A Speech Representation Codec for Speech Tokenization
by: Huang, Zhichao, et al.
Published: (2023)

Evaluating the Temporal Detection Capability of Integrated Gradients Applied on Sound Classifier
by: Dumpis, Martynas, et al.
Published: (2026)

Automatic Live Music Song Identification Using Multi-level Deep Sequence Similarity Learning
by: Hakala, Aapo, et al.
Published: (2025)

Noise-to-mask Ratio Loss for Deep Neural Network based Audio Watermarking
by: Moritz, Martin, et al.
Published: (2024)

Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis
by: Lin, Weiwei, et al.
Published: (2025)

VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis
by: Lin, Weiwei, et al.
Published: (2024)

Benchmarking Representations for Speech, Music, and Acoustic Events
by: La Quatra, Moreno, et al.
Published: (2024)

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
by: Hilmes, Benedikt, et al.
Published: (2025)

Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement
by: Yang, Yudong, et al.
Published: (2024)

The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval
by: Garcia-Martinez, Jaime, et al.
Published: (2025)

Dependence on Early and Late Reverberation of Single-Channel Speaker Distance Estimation
by: Neri, Michael, et al.
Published: (2026)

ASTRA: Aligning Speech and Text Representations for Asr without Sampling
by: Gaur, Neeraj, et al.
Published: (2024)

Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification
by: Morocutti, Tobias, et al.
Published: (2025)