In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-region through a learnable dictionary encoding layer. These embeddings are concatenated to obtain the final speaker representation. The SPE layer not only generates a fixed-dimensional speaker embedding for a variable-length speech segment, but also aggregates the information of feature distribution from multi-level temporal bins. Furthermore, we apply deep length normalization by augmenting the loss function with ring loss. By applying ring loss, the network gradually learns to normalize the speaker embeddings using model weights themselves while preserving convexity, leading to more robust speaker embeddings. Experiments on the VoxCeleb1 dataset show that the proposed system using the SPE layer and ring loss-based deep length normalization outperforms both ivector and d-vector baselines. Index Terms: speaker verification, spatial pyramid encoding, learnable dictionary encoding, ring loss, length normalization
d-vector systemsWe can classify d-vector based SV systems according to the loss function used. The first one is based on the softmax loss defined in [23] as the combination of a cross-entropy loss, a softmax function and the last fully connected layer [7,8,24]. In this system, a speaker classifier is trained to classify speakers in the training set. The softmax loss encourages the separability of speaker embeddings. However, the softmax loss is not sufficient to learn the discriminative embedding with a large margin, and more researchers began to explore discriminative loss functions for enhanced generalization ability.
In realistic settings, a speaker recognition system needs to identify a speaker given a short utterance, while the utterance used to enroll may be relatively long. However, existing speaker recognition models perform poorly with such short utterances. To solve this problem, we introduce a meta-learning scheme with imbalance length pairs. Specifically, we use a prototypical network and train it with a support set of long utterances and a query set of short utterances. However, since optimizing for only the classes in the given episode is not sufficient to learn discriminative embeddings for other classes in the entire dataset, we additionally classify both support set and query set against the entire classes in the training set to learn a well-discriminated embedding space. By combining these two learning schemes, our model outperforms existing state-of-the-art speaker verification models learned in a standard supervised learning framework on short utterance (1-2 seconds) on VoxCeleb dataset. We also validate our proposed model for unseen speaker identification, on which it also achieves significant gain over existing approaches.
Voice activity detection (VAD) is a challenging task in very low signal-to-noise ratio (SNR) environments. To address this issue, a promising approach is to map noisy speech features to corresponding clean features and to perform VAD using the generated clean features. This can be implemented by concatenating a speech enhancement (SE) and a VAD network, whose parameters are jointly updated. In this paper, we propose denoising variational autoencoder-based (DVAE) speech enhancement in the joint learning framework. Moreover, we feed not only the enhanced feature but also the latent code from the DVAE into the VAD network. We show that the proposed joint learning approach outperforms conventional denoising autoencoder-based joint learning approach.
Voice activity detection (VAD), which classifies frames as speech or non-speech, is an important module in many speech applications including speaker verification. In this paper, we propose a novel method, called self-adaptive soft VAD, to incorporate a deep neural network (DNN)-based VAD into a deep speaker embedding system. The proposed method is a combination of the following two approaches. The first approach is soft VAD, which performs a soft selection of frame-level features extracted from a speaker feature extractor. The frame-level features are weighted by their corresponding speech posteriors estimated from the DNN-based VAD, and then aggregated to generate a speaker embedding. The second approach is self-adaptive VAD, which fine-tunes the pre-trained VAD on the speaker verification data to reduce the domain mismatch. Here, we introduce two unsupervised domain adaptation (DA) schemes, namely speech posteriorbased DA (SP-DA) and joint learning-based DA (JL-DA). Experiments on a Korean speech database demonstrate that the verification performance is improved significantly in realworld environments by using self-adaptive soft VAD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.