AutoSpeech: Neural Architecture Search for Speaker Recognition
- URL: http://arxiv.org/abs/2005.03215v2
- Date: Mon, 31 Aug 2020 15:53:27 GMT
- Title: AutoSpeech: Neural Architecture Search for Speaker Recognition
- Authors: Shaojin Ding, Tianlong Chen, Xinyu Gong, Weiwei Zha, Zhangyang Wang
- Abstract summary: We propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech.
Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times.
Results demonstrate that the derived CNN architectures significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.
- Score: 108.69505815793028
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Speaker recognition systems based on Convolutional Neural Networks (CNNs) are
often built with off-the-shelf backbones such as VGG-Net or ResNet. However,
these backbones were originally proposed for image classification, and
therefore may not be naturally fit for speaker recognition. Due to the
prohibitive complexity of manually exploring the design space, we propose the
first neural architecture search approach approach for the speaker recognition
tasks, named as AutoSpeech. Our algorithm first identifies the optimal
operation combination in a neural cell and then derives a CNN model by stacking
the neural cell for multiple times. The final speaker recognition model can be
obtained by training the derived CNN model through the standard scheme. To
evaluate the proposed approach, we conduct experiments on both speaker
identification and speaker verification tasks using the VoxCeleb1 dataset.
Results demonstrate that the derived CNN architectures from the proposed
approach significantly outperform current speaker recognition systems based on
VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model
complexity.
Related papers
- Three-class Overlapped Speech Detection using a Convolutional Recurrent
Neural Network [32.59704287230343]
The proposed approach classifies into three classes: non-speech, single speaker speech, and overlapped speech.
A convolutional recurrent neural network architecture is explored to benefit from both convolutional layer's capability to model local patterns and recurrent layer's ability to model sequential information.
The proposed overlapped speech detection model establishes a state-of-the-art performance with a precision of 0.6648 and a recall of 0.3222 on the DIHARD II evaluation set.
arXiv Detail & Related papers (2021-04-07T03:01:34Z) - EfficientTDNN: Efficient Architecture Search for Speaker Recognition in
the Wild [29.59228560095565]
We propose a neural architecture search-based efficient time-delay neural network (EfficientTDNN) to improve inference efficiency while maintaining recognition accuracy.
Experiments on the VoxCeleb dataset show EfficientTDNN provides a huge search space including approximately $1013$s and achieves 1.66% EER and 0.156 DCF$_0.01$ with 565M MACs.
arXiv Detail & Related papers (2021-03-25T03:28:07Z) - Speech Command Recognition in Computationally Constrained Environments
with a Quadratic Self-organized Operational Layer [92.37382674655942]
We propose a network layer to enhance the speech command recognition capability of a lightweight network.
The employed method borrows the ideas of Taylor expansion and quadratic forms to construct a better representation of features in both input and hidden layers.
This richer representation results in recognition accuracy improvement as shown by extensive experiments on Google speech commands (GSC) and synthetic speech commands (SSC) datasets.
arXiv Detail & Related papers (2020-11-23T14:40:18Z) - Decentralizing Feature Extraction with Quantum Convolutional Neural
Network for Automatic Speech Recognition [101.69873988328808]
We build upon a quantum convolutional neural network (QCNN) composed of a quantum circuit encoder for feature extraction.
An input speech is first up-streamed to a quantum computing server to extract Mel-spectrogram.
The corresponding convolutional features are encoded using a quantum circuit algorithm with random parameters.
The encoded features are then down-streamed to the local RNN model for the final recognition.
arXiv Detail & Related papers (2020-10-26T03:36:01Z) - The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker
Diarisation Challenge [6.6238321827660345]
This paper describes system setup of our submission to speaker diarisation track (Track 4) of VoxCeleb Speaker Recognition Challenge 2020.
Our diarisation system consists of a well-trained neural network based speech enhancement model as pre-processing front-end of input speech signals.
arXiv Detail & Related papers (2020-10-22T12:42:07Z) - Evolutionary Algorithm Enhanced Neural Architecture Search for
Text-Independent Speaker Verification [29.939687921618678]
We borrow the idea of neural architecture search(NAS) for the textindependent speaker verification task.
This paper proposes an evolutionary algorithm enhanced neural architecture search method called Auto-designed.
The experimental results demonstrate our NAS-based model outperforms state-of-the-art speaker verification models.
arXiv Detail & Related papers (2020-08-13T05:34:52Z) - Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks [61.76338096980383]
A range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper- parameters of state-of-the-art factored time delay neural networks (TDNNs)
These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training.
Experiments conducted on a 300-hour Switchboard corpus suggest the auto-configured systems consistently outperform the baseline LF-MMI TDNN systems.
arXiv Detail & Related papers (2020-07-17T08:32:11Z) - Many-to-Many Voice Transformer Network [55.17770019619078]
This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework.
It enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech.
arXiv Detail & Related papers (2020-05-18T04:02:08Z) - Deep Speaker Embeddings for Far-Field Speaker Recognition on Short
Utterances [53.063441357826484]
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions.
Speaker verification on short utterances in uncontrolled noisy environment conditions is one of the most challenging and highly demanded tasks.
This paper presents approaches aimed to achieve two goals: a) improve the quality of far-field speaker verification systems in the presence of environmental noise, reverberation and b) reduce the system qualitydegradation for short utterances.
arXiv Detail & Related papers (2020-02-14T13:34:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.