A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement
Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a multiscale autoencoder (MSAE) for mask-based end-to-end neural network speech enhancement. The MSAE performs spectral decomposition of an input waveform within separate band-limited branches, each operating with a different rate and scale, to extract a sequence of multiscale embeddings. The proposed framework features intuitive parameterization of the autoencoder, including a flexible spectral band design based on the Constant-Q transform. Additionally, the MSAE is constructed entirely of differentiable operators, allowing it to be implemented within an end-to-end neural network, and be discriminatively trained. The MSAE draws motivation both from recent multiscale network topologies and from traditional multiresolution transforms in speech processing. Experimental results show the MSAE to provide clear performance benefits relative to conventional single-branch autoencoders. Additionally, the proposed framework is shown to outperform a variety of state-of-the-art enhancement systems, both in terms of objective speech quality metrics and automatic speech recognition accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionSpeech Enhancementspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to impr…
Generative Adversarial NetworkImage CompressionLightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devices
Time-series anomaly detection is increasingly important in IoT systems, sensor networks, and edge monitoring applications, where models must operate under strict constraints on memory, latency, and power consumption. Whi…
Anomaly DetectionInterpreting CLIP with Hierarchical Sparse Autoencoders
Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover i…
Attribution-Guided Distillation of Matryoshka Sparse Autoencoders
Sparse autoencoders (SAEs) aim to disentangle model activations into monosemantic, human-interpretable features. In practice, learned features are often redundant and vary across training runs and sparsity levels, which …
Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better r…
Speech EnhancementTriplet