The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve robustness of speaker representations to both intrinsic factors that are acquired during speech production (e.g., emotion, lexical content) and extrinsic factors that are acquired during signal capture (e.g., channel, noise). Disentanglement in neural speaker representations can be achieved either in a supervised fashion with annotations of the nuisance factors (factors not related to speaker identity) or in an unsupervised fashion without labels of the factors to be removed. In either case it is important to understand the extent to which the various factors of variability are entangled in the representations. In this work, we examine speaker representations with and without unsupervised disentanglement for the amount of information they capture related to a suite of factors. Using classification experiments we provide empirical evidence that disentanglement reduces the information with respect to nuisance factors from speaker representations, while retaining speaker information. This is further validated by speaker verification experiments on the VOiCES corpus in several challenging acoustic conditions. We also show improved robustness in speaker verification tasks using data augmentation during training of disentangled speaker embeddings. Finally, based on our findings, we provide insights into the factors that can be effectively separated using the unsupervised disentanglement technique and discuss potential future directions.
Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based methods are known to suffer from severe performance degradation when dealing with speech samples with different conditions (e.g., recording devices, emotional states). In this paper, we propose a novel fully supervised training method for extracting a speaker embedding vector disentangled from the variability caused by the nuisance attributes. The proposed framewo…
Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features via mutual information (MI) minimization. To achieve our goal of minimizing MI between speaker-related and speaker-unrelated features, we adopt a contrastive log-ratio upper bound (CLUB), which exploits the upper bound of MI. Our framework is constructed in a 3-stage structure. First, in the front-end encoder, input speech is encoded into shared initial embe…
Key Laboratory of Network Assessment Technology, Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所网络评估技术重点实验室）；Beijing Key Laboratory of Network Security and Protection Technology, Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所北京网络安全与防护技术重点实验室）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the speech samples may contain lots of identity-unrelated information, e.g., background noise, reverberation, emotion, etc. Previous works focus on optimizing the model to improve verification accuracy, without taking into account the elimination of the impact from the identity-unrelated information. To solve the above problem, we propose SEEF-ALDR, a novel Speake…
Center for Robust Speech Systems, The University of Texas at Dallas（德克萨斯大学达拉斯分校鲁棒语音系统中心）
Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to disentangle speaker-related and domain-specific features and apply domain adaptation on the speaker-related feature space solely. Instead of performing domain adaptation directly on the feature space where domain information is not removed, using disentanglement can efficiently boost adaptation performance. To be specific, our model's input speech from the source a…
Causally Disentangled Contrastive Learning for Multilingual Speaker Embeddings
Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）；Department of Computer Science and Technology, SUNY Empire State University（SUNY帝国州大学计算机科学与技术系）
Centre for Intelligent Sensing, Queen Mary University of London（伦敦玛丽女王大学智能感知中心）
Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers. Learning privacy-preserving representations for speech signals enables downstream tasks without sharing unnecessary, private information about an individual. In this paper, we show that protecting gender information in speech is more effective than modelling speaker-identity information only when generating a non-sensitive representation of speech. Our method relies on reconstructing speech by decoding linguistic content along with gender information using a variational autoencoder.…
Center for Language and Speech Processing（语言与语音处理中心）；Human Language Technology Center of Excellence（人类语言技术卓越中心）；The Johns Hopkins University（约翰斯·霍普金斯大学）
Deep neural network based speaker embeddings, such as x-vectors, have been shown to perform well in text-independent speaker recognition/verification tasks. In this paper, we use simple classifiers to investigate the contents encoded by x-vector embeddings. We probe these embeddings for information related to the speaker, channel, transcription (sentence, words, phones), and meta information about the utterance (duration and augmentation type), and compare these with the information encoded by i-vectors across a varying number of dimensions. We also study the effect of data augmentation during…
In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing solely speakercharacteristic information in order to be robust in terms of intra-speaker variations. By modifying the network architecture togenerate both speaker-related and speaker-unrelated representa-tions, we exploit a learning criterion which minimizes the mu-tual information between these disentangled embeddings. Wealso introduce an identity change loss cr…
In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features was reduced in the speaker embedding encoding. Therefore, we propose masked cross self-attentive encoding (MCSAE) using ResNet. It focuses on the features of both high-level and lowlevel layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, cross self-attention module is trained the interd…
Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
University of Eastern Finland（东芬兰大学）；City University of Hong Kong（香港城市大学）；University of Southampton（南安普顿大学）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels according to the similarities between speech features and given speaker embeddings. Our method is further extended and integrated with downstream tasks by utilizing the textual information, which has not been well studied in previous literature. The…
Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs). In this work, we learn representations that capture speaker identities by…
University of Science and Technology of China（中国科学技术大学）
This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of…
We study the problem of cross-lingual voice conversion in non-parallel speech corpora and one-shot learning setting. Most prior work require either parallel speech corpora or enough amount of training data from a target speaker. However, we convert an arbitrary sentences of an arbitrary source speaker to target speaker's given only one target speaker training utterance. To achieve this, we formulate the problem as learning disentangled speaker-specific and context-specific representations and follow the idea of [1] which uses Factorized Hierarchical Variational Autoencoder (FHVAE). After train…
Recently, hyperspherical embeddings have established themselves as a dominant technique for face and voice recognition. Specifically, Euclidean space vector embeddings are learned to encode person-specific information in their direction while ignoring the magnitude. However, recent studies have shown that the magnitudes of the embeddings extracted by deep neural networks may indicate the quality of the corresponding inputs. This paper explores the properties of the magnitudes of the embeddings related to quality assessment and out-of-distribution detection. We propose a new probabilistic speak…
University of Southern California（南加州大学）；Weill Cornell Medicine（威尔康奈尔医学院）；University of California Los Angeles（加州大学洛杉矶分校）；University of California, San Francisco（加州大学旧金山分校）
In this work, we propose deep latent space clustering for speaker diarization using generative adversarial network (GAN) backprojection with the help of an encoder network. The proposed diarization system is trained jointly with GAN loss, latent variable recovery loss, and a clustering-specific loss. It uses x-vector speaker embeddings at the input, while the latent variables are sampled from a combination of continuous random variables and discrete one-hot encoded variables using the original speaker labels. We benchmark our proposed system on the AMI meeting corpus, and two child-clinician i…
University of Edinburgh（爱丁堡大学）；Tokyo Institute of Technology（东京工业大学）
We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate this problem, we have incorporated a speaker encoder and speaker VQ codebook that learns global speaker characteristics entirely separate from the existing sub-phone codebooks. We also compare two training methods: self-supervised with global conditions and semi-supervised with speaker labels. Adding a speaker VQ component improves objective measures of spe…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input …
Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with the power set, which represents the possible combinations of target speakers. This formulation has two benefits. First, the overlaps of target speakers are explicitly modeled. Second, threshold selection is no longer needed. Through this formulation, we propose the speaker embedding-aware neural diarization (SEND) framework, where a speech encoder, a speaker…
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（洛林计算机科学及其应用研究所）；LIUM（勒芒大学信息实验室）；Le Mans Université（勒芒大学）
Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to transform a speech signal to remove the source speaker's identity while leaving the spoken content unchanged. Current methods perform the transformation by relying on content/speaker disentanglement and voice conversion. Usually, an acoustic model from an automatic speech recognition system extracts the content representation while an x-vector system extracts the speaker representation. Prior work has shown that the e…
In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content, speaker characteristics, and speaking style. To disentangle content and speaker representations, we propose a training strategy based on Siamese networks that encourages similarity between the content representations of the original and pitch-shifted audio. Next, we develop a synthesis model with pitch and duration predictors that can effectively reconstruct…
Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker. In this paper, we propose an adversarial learning framework for voice conversion, with which a single model can be trained to convert the voice to many different speakers, all without parallel data, by separating the speaker characteristics from the linguistic content in speech signals. An autoencoder is first trained to extract speaker-independent latent rep…
University of Oxford（牛津大学）；Naver Corporation（Naver公司）
The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces and audio in video. The key idea behind our approach is to tease apart--without annotation--the representations of linguistic content and speaker identity. We construct a two-stream architecture which: (1) shares low-level features common to both representations; and (2) provides a natural mechanism for explicitly disentangling these factors, offering the pot…
Centre for Speech Technology Research, University of Edinburgh（爱丁堡大学语音技术研究中心）；National Institute for Informatics（国立情报学研究所）
This work examines the content and usefulness of disentangled phone and speaker representations from two separately trained VQ-VAE systems: one trained on multilingual data and another trained on monolingual data. We explore the multi- and monolingual models using four small proof-of-concept tasks: copy-synthesis, voice transformation, linguistic code-switching, and content-based privacy masking. From these tasks, we reflect on how disentangled phone and speaker representations can be used to manipulate speech in a meaningful way. Our experiments demonstrate that the VQ representations are sui…
This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages. Frame label acquisition is an essential step in solving this problem. High quality frame labels should be in good consistency with golden transcriptions and robust to speaker variation. We propose to improve frame label acquisition in our previously adopted deep neural network-bottleneck feature (DNN-BNF) architecture by applying the factorized hierarchical vari…
Paderborn Center for Parallel Computing（帕德博恩并行计算中心）
In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches.…
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…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Google LLC（谷歌有限责任公司）
We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance information; and (3) a conditional decoder that reconstructs speech given local and global latent variables. Our experiments show that (1) the local latent variables encode speech contents, as reconstructed speech can be recognized by ASR with low word error rates (WER), even with a different global encoding; (2) the global latent variables encode speaker styl…
Speech intelligibility assessment plays an important role in the therapy of patients suffering from pathological speech disorders. Automatic and objective measures are desirable to assist therapists in their traditionally subjective and labor-intensive assessments. In this work, we investigate a novel approach for obtaining such a measure using the divergence in disentangled latent speech representations of a parallel utterance pair, obtained from a healthy reference and a pathological speaker. Experiments on an English database of Cerebral Palsy patients, using all available utterances per sp…
The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence, CUHK（香港中文大学感知与交互智能中心）；Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems（清华-香港中文大学媒体科学、技术与系统联合研究中心）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tsinghua University（清华大学）
We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by $β$-VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations show…
Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study, we investigate zero-shot VC from a novel perspective of self-supervised disentangled speech representation learning. Specifically, we achieve the disentanglement by balancing the information flow between global speaker representation and time-varying content representation in a sequential variational autoencoder (VAE). A zero-shot voice conversion is perform…
One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity and speech content, a task that still remains challenging. Here, we propose a novel approach to learning disentangled speech representation by transfer learning from style-based text-to-speech (TTS) models. With cycle consistent and adversarial training, the style-based TTS models can perform transcription-guided one-shot VC with high fidelity and similarity. …
Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；University of Science and Technology of China（中国科学技术大学）；Huya Inc (Shenzhen) Co., Ltd.（虎牙信息科技（深圳）有限公司）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions, limiting their application in the complex auditory scene. Towards the cocktail party problem, we propose a novel audio-visual speech separation model. In our model, we use the face detector to detect the number of speakers in the scene and use visual information to avoid the permutation problem. To improve our model's generalization ability to unknown speakers, w…
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery is formulated as a pipeline of phonetically discriminative feature learning and unit inference. One major difficulty in robust unsupervised feature learning is dealing with speaker variation. Here the robustness towards speaker variation is achieved by applying adversarial training and FHVAE based disentangled speech representation learning. A comparison of…
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (f…
