Progressive loss functions for speech enhancement with deep neural networks
نویسندگان
چکیده
Abstract The progressive paradigm is a promising strategy to optimize network performance for speech enhancement purposes. Recent works have shown different strategies improve the accuracy of solutions based on this mechanism. This paper studies using convolutional and residual neural architectures explores two criteria loss function optimization: weighted uniform progressive. work carries out evaluation simulated real samples with reverberation added noise REVERB VoiceHome datasets. Experimental results show variety achievements among optimization architectures. Results that design strengthens model increases robustness distortions due noise.
منابع مشابه
Text-informed speech enhancement with deep neural networks
A speech signal captured by a distant microphone is generally contaminated by background noise, which severely degrades the audible quality and intelligibility of the observed signal. To resolve this issue, speech enhancement has been intensively studied. In this paper, we consider a text-informed speech enhancement, where the enhancement process is guided by the corresponding text information,...
متن کاملOn Loss Functions for Deep Neural Networks in Classification
Deep neural networks are currently among the most commonly used classifiers. Despite easily achieving very good performance, one of the best selling points of these models is their modular design – one can conveniently adapt their architecture to specific needs, change connectivity patterns, attach specialised layers, experiment with a large amount of activation functions, normalisation schemes...
متن کاملRobust Loss Functions under Label Noise for Deep Neural Networks
In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate app...
متن کاملSpeech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks
In this paper we consider the problem of speech enhancement in real-world like conditions where multiple noises can simultaneously corrupt speech. Most of the current literature on speech enhancement focus primarily on presence of single noise in corrupted speech which is far from real-world environments. Specifically, we deal with improving speech quality in office environment where multiple s...
متن کاملAutomatic Speech Recognition with Deep Neural Networks for Impaired Speech
Automatic Speech Recognition has reached almost human performance in some controlled scenarios. However, recognition of impaired speech is a difficult task for two main reasons: data is (i) scarce and (ii) heterogeneous. In this work we train different architectures on a database of dysarthric speech. A comparison between architectures shows that, even with a small database, hybrid DNN-HMM mode...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Eurasip Journal on Audio, Speech, and Music Processing
سال: 2021
ISSN: ['1687-4722', '1687-4714']
DOI: https://doi.org/10.1186/s13636-020-00191-3