This paper explores three novel approaches to improve the performance of speaker verification (SV) systems based on deep neural networks (DNN) using Multi-head Self-Attention (MSA) mechanisms and memory layers. Firstly, we propose the use of a learnable vector called Class token to replace the average global pooling mechanism to extract the embeddings. Unlike global average pooling, our proposal takes into account the temporal structure of the input what is relevant for the text-dependent SV task. The class token is concatenated to the input before the first MSA layer, and its state at the output is used to predict the classes. To gain additional robustness, we introduce two approaches. First, we have developed a Bayesian estimation of the class token. Second, we have added a distilled representation token for training a teacher-student pair of networks using the Knowledge Distillation (KD) philosophy, which is combined with the class token. This distillation token is trained to mimic the predictions from the teacher network, while the class token replicates the true label. All the strategies have been tested on the RSR2015-Part II and DeepMine-Part 1 databases for text-dependent SV, providing competitive results compared to the same architecture using the average pooling mechanism to extract average embeddings.
The Chinese University of Hong Kong（香港中文大学）；Meituan（美团）
Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On the other hand, light-weight models are highly desired in practice despite their sub-optimal performance. This research aims to improve light-weight SR models through large-scale label-free knowledge distillation (KD). Existing KD approaches for SR typically require speaker labels to learn task-specific knowledge, due to the inefficiency of conventional los…
Most state-of-the-art Deep Learning systems for speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode variable-length utterances into fixed-length speaker vectors. In this paper we present Double Multi-Head Attention pooling, which extends our previous approach based on Self Multi-Head Attention. An additional self attention layer is added to the pooling layer that summarizes the context vectors produced by Multi-Head Attention into a unique speaker representation. This …
In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more promising way to solve it. Compared with contrastive learning, self-distilled approaches use only positive samples in the loss function and thus are more attractive. In this paper, we present a comprehensive study on self-distilled self-supervised speaker representation learning, especially on critical data augmentation. Our proposed strategy of audio perturbation a…
This paper describes the multi-query multi-head attention (MQMHA) pooling and inter-topK penalty methods which were first proposed in our submitted system description for VoxCeleb speaker recognition challenge (VoxSRC) 2021. Most multi-head attention pooling mechanisms either attend to the whole feature through multiple heads or attend to several split parts of the whole feature. Our proposed MQMHA combines both these two mechanisms and gain more diversified information. The margin-based softmax loss functions are commonly adopted to obtain discriminative speaker representations. To further en…
Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training effectiveness of SA-EEND models, we propose the use of auxiliary losses for the SA heads of the transformer layers. Specifically, we assume that the attention weight matrices of an SA layer are redundant if their patterns are similar to those of the identity matrix. We then explicitly constrain such matrices to exhibit specific speaker activity patterns relevant…
This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level representation. Inspired by the Transformer network, our proposed method utilizes the hierarchical architecture of stacked self-attention mechanisms to derive refined features that are more correlated with speakers. Serialized attention mechanism contains a stack of self-attention modules to create fixed-dimensional representations of speakers. Instead of utilizing m…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with additional output heads: a count-head to infer the number of speakers, and decoder-heads for reconstructing the original signals. Beyond the model, we also propose a metric on how to evaluate source separation with variable number of speakers. Specifically, we cleared up the issue on how to evaluate the quality when the ground-truth hasmore or less speakers than the ones predicted by the model. We evaluate our approach …
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to obtain an utterance level speaker representation. In this work we propose the use of an attention mechanism to obtain a discriminative speaker embedding given non fixed length speech utterances. Our system is based on a Convolutional Neural Network (CNN) that encodes short-term speaker features from the spectrogram and a self multi-head attention model that ma…
Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；National Institute of Information and Communications Technology, Japan（日本信息通信研究机构）；University of Washington（华盛顿大学）；University of Copenhagen（哥本哈根大学）
Tsinghua University（清华大学）；Unit, Chinese People's Liberation Army（中国人民解放军62315部队）
The pooling layer is an essential component in the neural network based speaker verification. Most of the current networks in speaker verification use average pooling to derive the utterance-level speaker representations. Average pooling takes every frame as equally important, which is suboptimal since the speaker-discriminant power is different between speech segments. In this paper, we present a unified attention-based pooling framework and combine it with the multi-head attention. Experiments on the Fisher and NIST SRE 2010 dataset show that involving outputs from lower layers to compute th…
Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for…
Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of convolutional neural network (CNN) in KD is to embed a dataset so as to perform a given task well, it is very important to acquire knowledge that considers intra-data relations. Conventional KD methods have concentrated on distilling knowledge in data units. To our knowledge, any KD methods for distilling information in dataset units have not yet been proposed.…
In forensic applications, it is very common that only small naturalistic datasets consisting of short utterances in complex or unknown acoustic environments are available. In this study, we propose a pipeline solution to improve speaker verification on a small actual forensic field dataset. By leveraging large-scale out-of-domain datasets, a knowledge distillation based objective function is proposed for teacher-student learning, which is applied for short utterance forensic speaker verification. The objective function collectively considers speaker classification loss, Kullback-Leibler diverg…
Worcester Polytechnic Institute (WPI)（伍斯特理工学院（WPI））
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding models contain a function f that separates speech from different speakers. In addition, they include a composition function g to compute set-union operations in the embedding space so as to infer the set of speakers within the input audio. In an experiment on multi-person speaker identification using synthesized LibriSpeech data, the proposed method outperform…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various methods differ in how the intermediate features of the student are encouraged to match those of the teacher. In this paper, we propose a simple-to-implement method using auxiliary classifiers at intermediate layers for matching features, which we refer to as multi-head knowledge distillation (MHKD). We add loss terms for training the student that measure the dissi…
Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed model contains a frame-level encoder and segment-level encoder, both of them make use of the transformer encoder block. The multi-head attention mechanism in the transformer structure could better capture different speaker properties when the input utterance contains multiple speakers. The memory mechanism used in the frame-level encoders can build a recurren…
Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our modular method can be straightforwardly applied with any neural topic model to improve topic quality, which we demonstrate using two models having disparate architectures, obtaining state-of-the-art topic coherence. We show that our adaptable framework not only improves performance in the aggregate over all estimated topics, as is commonly reported, but als…
Due to the high performance of multi-channel speech processing, we can use the outputs from a multi-channel model as teacher labels when training a single-channel model with knowledge distillation. To the contrary, it is also known that single-channel speech data can benefit multi-channel models by mixing it with multi-channel speech data during training or by using it for model pretraining. This paper focuses on speaker diarization and proposes to conduct the above bi-directional knowledge transfer alternately. We first introduce an end-to-end neural diarization model that can handle both sin…
Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a new transformer based pooling structure called PoFormer to enhance the ability of the pooling layer to capture information along the whole time axis. Different from previous works that apply attention mechanism in a simple way or implement the multi-head mechanism in serial instead of in parallel, PoFormer follows the initial transformer structure with some …
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Capturing long-range dependency and modeling long temporal contexts is proven to benefit speaker verification tasks. In this paper, we propose the combination of the Hierarchical-Split block(HS-block) and the Depthwise Separable Self-Attention(DSSA) module to capture richer multi-range context speaker features from a local and global perspective respectively. Specifically, the HS-block splits the feature map and filters into several groups and stacks them in one block, which enlarges the receptive fields(RFs) locally. The DSSA module improves the multi-head self-attention mechanism by the dept…
Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional self-attention mechanisms are originally designed for modeling textual sequence without considering the characteristics of speech and speaker modeling. Besides, different Transformer variants for speaker recognition have not been well studied. In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer vari…
The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and student (i.e., capacity gap), knowledge distillation loses its strength in transferring knowledge from the teacher to the student, thus training a weaker student. To mitigate the impact of the capacity gap, we introduce knowledge distillation via intermediate heads. By extending the intermediate layers of the teacher (at various depths) with classifier heads, we c…
This paper describes a method for overlap-aware speaker diarization. Given an overlap detector and a speaker embedding extractor, our method performs spectral clustering of segments informed by the output of the overlap detector. This is achieved by transforming the discrete clustering problem into a convex optimization problem which is solved by eigen-decomposition. Thereafter, we discretize the solution by alternatively using singular value decomposition and a modified version of non-maximal suppression which is constrained by the output of the overlap detector. Furthermore, we detail an HMM…
School of Computer Science, Wuhan University（武汉大学计算机学院）；Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center, Duke Kunshan University（多模态智能系统苏州市重点实验室、创新数字研究中心、杜克昆山大学）
Imperial College London（帝国理工学院）；University of Amsterdam（阿姆斯特丹大学）；ETH Zurich（苏黎世联邦理工学院）；University of Warsaw（华沙大学）；Google Research（谷歌研究院）；University of California, Irvine（加州大学欧文分校）
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden of the ensemble while trying to preserve its predictive behavior. Most existing distillation formulations summarize the ensemble by capturing its average predictions. As a result, the diversity of the ensemble predictions, stemming from each member, is lost. Thus, the distilled mo…
Ajou University（亚洲大学）；Hyundai Motor Company（现代汽车公司）；Naver AI Lab（Naver人工智能实验室）
Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational efficiency. In this paper, we first propose an autoencoder-style framework comprising channel-wise compression and decompression via interchange transfer-based knowledge distillation. To learn the map-view feature of a teacher network, the features from teacher and student networks are independently passed through the shared autoencoder; here, we use a compress…
We present a unified network for voice separation of an unknown number of speakers. The proposed approach is composed of several separation heads optimized together with a speaker classification branch. The separation is carried out in the time domain, together with parameter sharing between all separation heads. The classification branch estimates the number of speakers while each head is specialized in separating a different number of speakers. We evaluate the proposed model under both clean and noisy reverberant set-tings. Results suggest that the proposed approach is superior to the baseli…
