Search Results for author:
Found 9 papers, 7 papers with code
CATSE: A Context-Aware Framework for Causal Target Sound Extraction
First, we explore the utility of context by providing the TSE model with oracle information about what sound classes make up the input mixture, where the objective of the model is to extract one or more sources of interest indicated by the user.
Latent CLAP Loss for Better Foley Sound Synthesis
We introduce a new loss term to enhance Foley sound generation in AudioLDM without post-filtering.
Two-Step Knowledge Distillation for Tiny Speech Enhancement
Tiny, causal models are crucial for embedded audio machine learning applications.
Self-Supervised Learning for Speech Enhancement through Synthesis
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction.
BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping
Our results indicate that the hybrid model with a convolutional transformer as the encoder yields superior performance in most HEAR challenge tasks.
Ranked #1 on
Self-Supervised Learning
on CREMA-D
Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load
To that end, we introduce a set of five datasets for task load detection in speech.
SERAB: A multi-lingual benchmark for speech emotion recognition
To facilitate the process, here, we present the Speech Emotion Recognition Adaptation Benchmark (SERAB), a framework for evaluating the performance and generalization capacity of different approaches for utterance-level SER.
Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing
Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
Deep speech inpainting of time-frequency masks
To address these limitations, here we propose an end-to-end framework for speech inpainting, the context-based retrieval of missing or severely distorted parts of time-frequency representation of speech.
