Wu Guo

Chenyang Guo, Liping Chen, Zhuhai Li et al.

Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has shown the positive use cases of the same technique to conceal speaker's voice attribute with additive perturbation signal generated by an adversarial network. This paper examines the reversibility property where an entity generating the adversarial perturbations is authorized to remove them and restore original speech (e.g., the speaker him/herself). A similar technique could also be used by an investigator to deanonymize a voice-protected speech to restore criminals' identities in security and forensic analysis. In this setting, the perturbation generative module is assumed to be known in the removal process. To this end, a joint training of perturbation generation and removal modules is proposed. Experimental results on the LibriSpeech dataset demonstrated that the subtle perturbations added to the original speech can be predicted from the anonymized speech while achieving the goal of privacy protection. By removing these perturbations from the anonymized sample, the original speech can be restored. Audio samples can be found in \url{https://voiceprivacy.github.io/Perturbation-Generation-Removal/}.

Tan Liu, Wu Guo, Bin Gu

Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classification (TTC) module to predict the topic class from the decoded text. In this paper, instead of using the ASR transcripts, the fusion of deep acoustic and linguistic features is used for topic classification on spoken documents. More specifically, a conventional CTC-based acoustic model (AM) using phonemes as output units is first trained, and the outputs of the layer before the linear phoneme classifier in the trained AM are used as the deep acoustic features of spoken documents. Furthermore, these deep acoustic features are fed to a phoneme-to-word (P2W) module to obtain deep linguistic features. Finally, a local multi-head attention module is proposed to fuse these two types of deep features for topic classification. Experiments conducted on a subset selected from Switchboard corpus show that our proposed framework outperforms the conventional ASR+TTC systems and achieves a 3.13% improvement in ACC.

Yafeng Chen, Wu Guo, Bin Gu

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly trained with the conventional cross entropy loss and prototypical networks (PN) loss. Then, inspired by speaker adaptive training in speech recognition, additional transformation coefficients are trained with only the PN loss. The transformation coefficients are used to modify the original backbone embedding network in the x-vector extraction process. Furthermore, the random erasing data augmentation technique is applied to all support samples in each episode to construct positive pairs, and a contrastive loss between the augmented and the original support samples is added to the objective in model training. Experiments are carried out on the SITW and VOiCES databases. Both of the methods can obtain consistent improvements over existing meta-learning training frameworks. By combining these two methods, we can observe further improvements on these two databases.

Yafeng Chen, Wu Guo, Jingjing Shi et al.

In this work, we introduce metric learning (ML) to enhance the deep embedding learning for text-independent speaker verification (SV). Specifically, the deep speaker embedding network is trained with conventional cross entropy loss and auxiliary pair-based ML loss function. For the auxiliary ML task, training samples of a mini-batch are first arranged into pairs, then positive and negative pairs are selected and weighted through their own and relative similarities, and finally the auxiliary ML loss is calculated by the similarity of the selected pairs. To evaluate the proposed method, we conduct experiments on the Speaker in the Wild (SITW) dataset. The results demonstrate the effectiveness of the proposed method.

Bin Gu, Wu Guo

The x-vector maps segments of arbitrary duration to vectors of fixed dimension using deep neural network. Combined with the probabilistic linear discriminant analysis (PLDA) backend, the x-vector/PLDA has become the dominant framework in text-independent speaker verification. Nevertheless, how to extract the x-vector appropriate for the PLDA backend is a key problem. In this paper, we propose a Gaussian noise constrained network (GNCN) to extract xvector, which adopts a multi-task learning strategy with the primary task classifying the speakers and the auxiliary task just fitting the Gaussian noises. Experiments are carried out using the SITW database. The results demonstrate the effectiveness of our proposed method

Bin Gu, Wu Guo

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution (MSCNN) is adopted in frame-level layers to capture complementary speaker information in different receptive fields. (2) A Baum-Welch statistics attention (BWSA) mechanism is applied in pooling-layer, which can integrate more useful long-term speaker characteristics in the temporal pooling layer. Experiments are carried out on the NIST SRE16 evaluation set. The results demonstrate the effectiveness of MSCNN and show the proposed BWSA can further improve the performance of the DNN embedding system

Fenglin Ding, Wu Guo, Lirong Dai et al.

Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch normalization (ABN) in Long Short Term Memory (LSTM) based acoustic modeling for automatic speech recognition (ASR). In the proposed method, an auxiliary network is used to dynamically generate the scaling and shifting parameters in batch normalization, and attention mechanisms are introduced to improve their regularized performance. Furthermore, two schemes, frame-level and utterance-level ABN, are investigated. We evaluate our proposed methods on Mandarin and Uyghur ASR tasks, respectively. The experimental results show that the proposed ABN greatly improves the performance of batch normalization in terms of transcription accuracy for both languages.

Lanhua You, Wu Guo, Lirong Dai et al.

In this paper, gating mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, a gated convolution neural network (GCNN) is employed for modeling the frame-level embedding layers. Compared with the time-delay DNN (TDNN), the GCNN can obtain more expressive frame-level representations through carefully designed memory cell and gating mechanisms. Moreover, we propose a novel gated-attention statistics pooling strategy in which the attention scores are shared with the output gate. The gated-attention statistics pooling combines both gating and attention mechanisms into one framework; therefore, we can capture more useful information in the temporal pooling layer. Experiments are carried out using the NIST SRE16 and SRE18 evaluation datasets. The results demonstrate the effectiveness of the GCNN and show that the proposed gated-attention statistics pooling can further improve the performance.

Lanhua You, Wu Guo, Lirong Dai et al.

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the primary task of classifying the target speakers, and the auxiliary task of reconstructing the first- and higher-order statistics of the original input utterance. The proposed training strategy aggregates both the supervised and unsupervised learning into one framework to make the speaker embeddings more discriminative and robust. Experiments are carried out using the NIST SRE16 evaluation dataset and the VOiCES dataset. The results demonstrate that our proposed method outperforms the original x-vector approach with very low additional complexity added.

Quan Liu, Wu Guo, Zhen-Hua Ling

This paper proposes an algorithm to improve the calculation of confidence measure for spoken term detection (STD). Given an input query term, the algorithm first calculates a measurement named document ranking weight for each document in the speech database to reflect its relevance with the query term by summing all the confidence measures of the hypothesized term occurrences in this document. The confidence measure of each term occurrence is then re-estimated through linear interpolation with the calculated document ranking weight to improve its reliability by integrating document-level information. Experiments are conducted on three standard STD tasks for Tamil, Vietnamese and English respectively. The experimental results all demonstrate that the proposed algorithm achieves consistent improvements over the state-of-the-art method for confidence measure calculation. Furthermore, this algorithm is still effective even if a high accuracy speech recognizer is not available, which makes it applicable for the languages with limited speech resources.