Mismatch between enrollment and test conditions causes serious performance degradation on speaker recognition systems. This paper presents a statistics decomposition (SD) approach to solve this problem. This approach decomposes the PLDA score into three components that corresponding to enrollment, prediction and normalization respectively. Given that correct statistics are used in each component, the resultant score is theoretically optimal. A comprehensive experimental study was conducted on three datasets with different types of mismatch: (1) physical channel mismatch, (2) speaking behavior mismatch, (3) near-far recording mismatch. The results demonstrated that the proposed SD approach is highly effective, and outperforms the ad-hoc multi-condition training approach that is commonly adopted but not optimal in theory.
Indian Institute of Information Technology (IIIT)（印度信息技术学院）；Aalborg University（奥尔堡大学）
Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced applications. SV involves training speaker-independent (SI) models and speaker-dependent models where speakers are represented by models derived from an SI model using the training data for the particular speaker during the enrollment phase. While data augmentation for training SI models is well studied, data augmentation for speaker enrollment is rarely ex…
Stabilizing Short Duration Speaker Verification through Neural Re-scoring with Hybrid Enrollment
Shanghai University, China（上海大学）；Xi’an Jiaotong-Liverpool University, China（西安交通大学利物浦大学）；Hithink RoyalFlush AI Research Institute, China（Hithink皇家Flush人工智能研究院）
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of multiple enrollment utterances, we propose a novel attention back-end model, which can be used for both text-independent (TI) and text-dependent (TD) speaker verification, and employ scaled-dot self-attention and feed-forward self-attention networks as architectures that learn the intra-relationships of the enrollment utterances. In order to verify the proposed attention back-end, …
Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic linear discriminant analysis (PLDA) or neural network-based neural PLDA (NPLDA) for similarity scoring. However, the sequential optimization of the front-end and back-end models may lead to a local minimum, which theoretically prevents the whole system from achieving the best optimization. Although some methods have been proposed for jointly optimizing the two m…
AI Lab, Lenovo Research（联想研究院人工智能实验室）；Data Science Research Center, Duke Kunshan University（昆山杜克大学数据科学研究中心）
With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging problem. Traditionally, a speaker verification system is symmetrical, indicating that the same embedding extraction model is applied for both enrollment and verification in inference. In this paper, we come up with an innovative asymmetric structure, which takes the large-scale ECAPA-TDNN model for enrollment and the small-scale ECAPA-TDNNLite model for verific…
School of Computing, University of Eastern Finland（东芬兰大学计算机学院）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林信息学及其应用研究实验室）
Speaker recognition on household devices, such as smart speakers, features several challenges: (i) robustness across a vast number of heterogeneous domains (households), (ii) short utterances, (iii) possibly absent speaker labels of the enrollment data (passive enrollment), and (iv) presence of unknown persons (guests). While many commercial products exist, there is less published research and no publicly-available evaluation protocols or open-source baselines. Our work serves to bridge this gap by providing an accessible evaluation benchmark derived from public resources (VoxCeleb and ASVspoo…
Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker. A typical deep learning TSS framework consists of an upstream model that obtains enrollment speaker embeddings and a downstream model that performs the separation conditioned on the embeddings. In this paper, we look into several important but overlooked aspects of the enrollment embeddings, including the suitability of the widely used speaker identification embeddings, the introduction of the log-mel filterbank and self-supervise…
Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University（智能教育与大数据上海工程研究中心，上海师范大学）；SHNU-Unisound Natural Human-Computer Interaction Lab, Shanghai Normal University（上海师范大学Unisound人机交互实验室）；Unisound AI Technology Co., Ltd.（Unisound人工智能技术有限公司）
Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteristics of the target speaker. One major difficulty of target speech extraction lies in handling variability in ``intra-speaker'' characteristics, i.e., characteristics mismatch between target speech and an enrollment utterance. While most conventional approaches focus on improving {\it average performance} given a set of enrollment utterances, here we propose to guarantee the {\it worst performance}, which we believe i…
Dominant researches adopt supervised training for speaker extraction, while the scarcity of ideally clean corpus and channel mismatch problem are rarely considered. To this end, we propose speaker-aware mixture of mixtures training (SAMoM), utilizing the consistency of speaker identity among target source, enrollment utterance and target estimate to weakly supervise the training of a deep speaker extractor. In SAMoM, the input is constructed by mixing up different speaker-aware mixtures (SAMs), each contains multiple speakers with their identities known and enrollment utterances available. Inf…
Duke Kunshan University（昆山杜克大学）；Beijing Shell Shell Technology Co. Ltd.（北京贝壳科技有限公司）；Wuhan University（武汉大学）
This paper presents a far-field text-dependent speaker verification database named HI-MIA. We aim to meet the data requirement for far-field microphone array based speaker verification since most of the publicly available databases are single channel close-talking and text-independent. The database contains recordings of 340 people in rooms designed for the far-field scenario. Recordings are captured by multiple microphone arrays located in different directions and distance to the speaker and a high-fidelity close-talking microphone. Besides, we propose a set of end-to-end neural network based…
Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion
School of Computer Science, Wuhan University, Wuhan, China（1 武汉大学计算机学院，武汉，中国）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China（2 香港中文大学（深圳）人工智能学院，中国）；School of Artificial Intelligence, Wuhan University, Wuhan, China（3 武汉大学人工智能学院，武汉，中国）；School of Cyber Science and Engineering, Wuhan University, Wuhan, China（4 武汉大学网络科学与工程学院，武汉，中国）；Digital Innovation Research Center, Duke Kunshan University, Kunshan, China（5 香港中文大学（深圳）数字创新研究中心，中国）；AI Center, OPPO, Beijing, China（6 OPPO人工智能中心，北京，中国）
This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario. First, we show that popular cosine scoring suffers from poor score calibration with a varying number of enrollment utterances. Second, we propose a simple replacement for cosine scoring based on an extremely constrained version of probabilistic linear discriminant analysis (PLDA). The proposed model improves over the cosine scoring for multi-enrollment recognition while keeping the same performanc…
In this paper, we propose a solution to allow speaker conditioned speech models, such as VoiceFilter-Lite, to support an arbitrary number of enrolled users in a single pass. This is achieved by using an attention mechanism on multiple speaker embeddings to compute a single attentive embedding, which is then used as a side input to the model. We implemented multi-user VoiceFilter-Lite and evaluated it for three tasks: (1) a streaming automatic speech recognition (ASR) task; (2) a text-independent speaker verification task; and (3) a personalized keyphrase detection task, where ASR has to detect…
Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems. The common wisdom is to collect cross-domain data and train a multi-domain PLDA model, with the hope to learn a domain-independent speaker subspace. In this paper, we firstly present an empirical study to show that simply adding cross-domain data does not help performance in conditions with enrollment-test mismatch. Careful analysis shows that this striking result is caused by the incoherent statistics between the enrollment and test conditions. Based on this analysis, we…
Listen to Extract: Onset-Prompted Target Speaker Extraction
Department of Computer Science, Inner Mongolia University（内蒙古大学计算机科学系）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；School of Automation and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学自动化与智能制造学院）
Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and relation networks for this use case. We propose improved relation networks for speaker verification and few-shot (unseen) speaker identification. The use of relation networks facilitates joint training of the frontend speaker encoder and the backend model. Inspired by the use of prototypical networks in speaker verification and to increase the discriminabilit…
In this paper, an architecture based on Long Short-Term Memory Networks has been proposed for the text-independent scenario which is aimed to capture the temporal speaker-related information by operating over traditional speech features. For speaker verification, at first, a background model must be created for speaker representation. Then, in enrollment stage, the speaker models will be created based on the enrollment utterances. For this work, the model will be trained in an end-to-end fashion to combine the first two stages. The main goal of end-to-end training is the model being optimized …
This paper presents a novel study of parameter-free attentive scoring for speaker verification. Parameter-free scoring provides the flexibility of comparing speaker representations without the need of an accompanying parametric scoring model. Inspired by the attention component in Transformer neural networks, we propose a variant of the scaled dot product attention mechanism to compare enrollment and test segment representations. In addition, this work explores the effect on performance of (i) different types of normalization, (ii) independent versus tied query/key estimation, (iii) varying th…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria-Loria（法国国家信息与自动化研究所-洛林计算机科学及其应用实验室）；Avignon Université（阿维尼翁大学）
Speaker verification (SV) suffers from unsatisfactory performance in far-field scenarios due to environmental noise andthe adverse impact of room reverberation. This work presents a benchmark of multichannel speech enhancement for far-fieldspeaker verification. One approach is a deep neural network-based, and the other is a combination of deep neural network andsignal processing. We integrated a DNN architecture with signal processing techniques to carry out various experiments. Ourapproach is compared to the existing state-of-the-art approaches. We examine the importance of enrollment in pre-…
Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities
University of Science and Technology Beijing（北京科技大学）；Beijing Institute of Technology（北京理工大学）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Alibaba Group（阿里巴巴集团）；Zhejiang Institute of Quality Sciences（浙江省质量科学研究院）；Tianjin University（天津大学）；Technical University of Munich（慕尼黑工业大学）
Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods rely on a probabilistic model to infer the speaker factor, so any significant change on the distribution of the speech signal will impact the inference. Recently, we proposed a deep learning model that can learn how to extract the speaker factor by a deep neural network (DNN). By this feature learning, an SV system can be constructed with a very simple back-…
Northwestern Polytechnical University（西北工业大学）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Tencent Media Lab（腾讯媒体实验室）
In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain mismatches in speaker recognition. However, usually both training and evaluation data themselves can be composed of several subsets. These inner variances of each dataset can also be considered as different domains. Different distributed subsets in source or target domain dataset can also cause multi-domain mismatches, which are influential to speaker recogni…
In this paper, we conduct a cross-dataset study on parametric and non-parametric raw-waveform based speaker embeddings through speaker verification experiments. In general, we observe a more significant performance degradation of these raw-waveform systems compared to spectral based systems. We then propose two strategies to improve the performance of raw-waveform based systems on cross-dataset tests. The first strategy is to change the real-valued filters into analytic filters to ensure shift-invariance. The second strategy is to apply variational dropout to non-parametric filters to prevent …
University of Science and Technology of China（中国科学技术大学）；iFlytek Research（科大讯飞研究院）；Georgia Institute of Technology（佐治亚理工学院）
We propose a separation guided speaker diarization (SGSD) approach by fully utilizing a complementarity of speech separation and speaker clustering. Since the conventional clustering-based speaker diarization (CSD) approach cannot well handle overlapping speech segments, we investigate, in this study, separation-based speaker diarization (SSD) which inherently has the potential to handle the speaker overlap regions. Our preliminary analysis shows that the state-of-the-art Conv-TasNet based speech separation, which works quite well on the simulation data, is unstable in realistic conversational…
Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions
Center for Speech and Language Technologies (CSLT), BNRist at Tsinghua University（语音与语言技术中心（CSLT），北京理工大学清华大学）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学）
Diarization partitions an audio stream into segments based on the voices of the speakers. Real-time diarization systems that include an enrollment step should limit enrollment training samples to reduce user interaction time. Although training on a small number of samples yields poor performance, we show that the accuracy can be improved dramatically using a chronological self-training approach. We studied the tradeoff between training time and classification performance and found that 1 second is sufficient to reach over 95% accuracy. We evaluated on 700 audio conversation files of about 10 m…
Escola Universitària Politècnica de Mataró（马塔罗理工学院）；University of Saarland（萨尔大学）
This paper presents an exhaustive study about the robustness of several parameterizations, with a new database specially acquired for the purpose of a speaker recognition application. This database includes the following variations: different recording sessions (including telephonic and microphonic recordings), recording rooms, and languages (it has been obtained from a bilingual set of speakers). This study has been performed with covariance matrices in a text independent speaker verification application. It reveals that the combination of several parameterizations can improve the robustness …
Target speech separation refers to isolating target speech from a multi-speaker mixture signal by conditioning on auxiliary information about the target speaker. Different from the mainstream audio-visual approaches which usually require simultaneous visual streams as additional input, e.g. the corresponding lip movement sequences, in our approach we propose the novel use of a single face profile of the target speaker to separate expected clean speech. We exploit the fact that the image of a face contains information about the person's speech sound. Compared to using a simultaneous visual sequ…
University of Eastern Finland（东芬兰大学）；School of Computing（计算机学院）
Modern automatic speaker verification (ASV) relies heavily on machine learning implemented through deep neural networks. It can be difficult to interpret the output of these black boxes. In line with interpretative machine learning, we model the dependency of ASV detection score upon acoustic mismatch of the enrollment and test utterances. We aim to identify mismatch factors that explain target speaker misses (false rejections). We use distance in the first- and second-order statistics of selected acoustic features as the predictors in a linear mixed effects model, while a standard Kaldi x-vec…
Queensland University of Technology（昆士兰科技大学）；University of Jaffna（贾夫纳大学）
This paper analyses the short utterance probabilistic linear discriminant analysis (PLDA) speaker verification with utterance partitioning and short utterance variance (SUV) modelling approaches. Experimental studies have found that instead of using single long-utterance as enrolment data, if long enrolled utterance is partitioned into multiple short utterances and average of short utterance i-vectors is used as enrolled data, that improves the Gaussian PLDA (GPLDA) speaker verification. This is because short utterance i-vectors have speaker, session and utterance variations, and utterance-par…
This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evaluation shows that the multi-class neural network system has superior performance for large population sizes.
Probabilistic Linear Discriminant Analysis (PLDA) has become state-of-the-art method for modeling $i$-vector space in speaker recognition task. However the performance degradation is observed if enrollment data size differs from one speaker to another. This paper presents a solution to such problem by introducing new PLDA scoring normalization technique. Normalization parameters are derived in a blind way, so that, unlike traditional \textit{ZT-norm}, no extra development data is required. Moreover, proposed method has shown to be optimal in terms of detection cost function. The experiments co…
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）
This paper describes the systems developed by the HCCL team for the NIST 2021 speaker recognition evaluation (NIST SRE21).We first explore various state-of-the-art speaker embedding extractors combined with a novel circle loss to obtain discriminative deep speaker embeddings. Considering that cross-channel and cross-linguistic speaker recognition are the key challenges of SRE21, we introduce several techniques to reduce the cross-domain mismatch. Specifically, Codec and speech enhancement are directly applied to the raw speech to eliminate the codecs and the environment noise mismatch. We deno…
This document describes the Short-duration Speaker Verification (SdSV) Challenge 2021. The main goal of the challenge is to evaluate new technologies for text-dependent (TD) and text-independent (TI) speaker verification (SV) in a short duration scenario. The proposed challenge evaluates SdSV with varying degree of phonetic overlap between the enrollment and test utterances (cross-lingual). It is the first challenge with a broad focus on systematic benchmark and analysis on varying degrees of phonetic variability on short-duration speaker recognition. We expect that modern methods (deep neural…
Recently in speaker recognition, performance degradation due to the channel domain mismatched condition has been actively addressed. However, the mismatches arising from language is yet to be sufficiently addressed. This paper proposes an approach which employs recursive whitening transformation to mitigate the language mismatched condition. The proposed method is based on the multiple whitening transformation, which is intended to remove un-whitened residual components in the dataset associated with i-vector length normalization. The experiments were conducted on the Speaker Recognition Evalu…
In speaker diarisation, speaker embedding extraction models often suffer from the mismatch between their training loss functions and the speaker clustering method. In this paper, we propose the method of spectral clustering-aware learning of embeddings (SCALE) to address the mismatch. Specifically, besides an angular prototype cal (AP) loss, SCALE uses a novel affinity matrix loss which directly minimises the error between the affinity matrix estimated from speaker embeddings and the reference. SCALE also includes p-percentile thresholding and Gaussian blur as two important hyper-parameters fo…
Korea University Intelligent Signal Processing Lab. (KU-ISPL) developed speaker recognition system for SRE16 fixed training condition. Data for evaluation trials are collected from outside North America, spoken in Tagalog and Cantonese while training data only is spoken English. Thus, main issue for SRE16 is compensating the discrepancy between different languages. As development dataset which is spoken in Cebuano and Mandarin, we could prepare the evaluation trials through preliminary experiments to compensate the language mismatched condition. Our team developed 4 different approaches to ext…
Duke Kunshan University（昆山杜克大学）；National University of Singapore（新加坡国立大学）；University of Southern California（南加州大学）；Wuhan University（武汉大学）
The INTERSPEECH 2020 Far-Field Speaker Verification Challenge (FFSVC 2020) addresses three different research problems under well-defined conditions: far-field text-dependent speaker verification from single microphone array, far-field text-independent speaker verification from single microphone array, and far-field text-dependent speaker verification from distributed microphone arrays. All three tasks pose a cross-channel challenge to the participants. To simulate the real-life scenario, the enrollment utterances are recorded from close-talk cellphone, while the test utterances are recorded f…
Enhancing Open-Set Speaker Identification through Rapid Tuning with Speaker Reciprocal Points and Negative Sample
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Communication（通信学院）；Information Engineering, Shanghai University（上海大学信息工程学院）
Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have degraded performance for multi-talker scenarios -- possibly due to the domain mismatch -- which severely limits their use for such applications. In this paper, we investigate the adaptation of upstream SSL models to the multi-talker automatic speech recognition (ASR) task under two conditions. First, when segmented utterances are given, we show that adding a target…
