In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts, which demonstrate equal error rates under 1% on the popular VoxCeleb1 test set. This paper proposes a novel speaker recognition model based on raw waveform inputs. The model incorporates recent advances in machine learning and speaker verification, including the Res2Net backbone module and multi-layer feature aggregation. Our best model achieves an equal error rate of 0.89%, which is competitive with the state-of-the-art models based on handcrafted features, and outperforms the best model based on raw waveform inputs by a large margin. We also explore the application of the proposed model in the context of self-supervised learning framework. Our self-supervised model outperforms single phase-based existing works in this line of research. Finally, we show that self-supervised pre-training is effective for the semi-supervised scenario where we only have a small set of labelled training data, along with a larger set of unlabelled examples.
University of Rochester（罗切斯特大学）；Beijing Institute of Technology（北京理工大学）
State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown competitive results. In this paper, we propose a novel multi-scale waveform encoder that uses three convolution branches with different time scales to compute speech features from the waveform. These features are then processed by squeeze-and-excitation blocks, a multi-level feature aggregator, and a time delayed neural network (TDNN) to compute speaker embeddi…
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 …
Aalto University（阿尔托大学）；University of Crete（克里特大学）；National Institute of Informatics（国立信息学研究所）
Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conversion. Furthermore, conditioning WaveNets with acoustic features allows sharing the waveform generator model across multiple speakers without additional speaker codes. However, multi-speaker WaveNet models require large amounts of training data and computation to cover the entire …
In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a large speaker-verification dataset which can extract a speaker embedding vector from an utterance pronounced by an arbitrary speaker. At the training stage, a speaker-aware WaveNet vocoder is then built using a multi-speaker dataset which adopts both acoustic feature sequences and speaker embedding vectors as conditions.At the generation stage, we first fee…
Voice conversion for speaker anonymization is an emerging field in speech processing research. Many state-of-the-art approaches are based on the resynthesis of the phoneme posteriorgrams (PPG), the fundamental frequency (F0) of the input signal together with modified X-vectors. Our research focuses on the role of F0 for speaker anonymization, which is an understudied area. Utilizing the VoicePrivacy Challenge 2020 framework and its datasets we developed and evaluated eight low-complexity F0 modifications prior resynthesis. We found that modifying the F0 can improve speaker anonymization by as …
Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring further investigation. In this study, we explore end-to-end deep neural networks that input raw waveforms to improve various aspects: front-end speaker embedding extraction including model architecture, pre-training scheme, additional objective functions, and back-end classification. Adjustment of model architecture using a pre-training scheme can extract speake…
Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly. Rather than employing standard hand-crafted features, the latter CNNs learn low-level speech representations from waveforms, potentially allowing the network to better capture important narrow-band speaker characteristics such as pitch and formants. Proper design of the neural network is crucial to achieve this goal. This paper proposes a novel CNN architec…
Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech representations from raw waveforms. On this basis, a CNN architecture called SincNet proposes a kind of unique convolutional layer, which has achieved band-pass filters. Compared with standard CNNs, SincNet learns the low and high cut-off frequencies of each filter. This paper proposes an improved CNNs architecture called PF-Net, which encourages the first convolution…
National Institute of Informatics（国立信息学研究所）；EURECOM（欧洲通信研究院）；University of Avignon（阿维尼翁大学）
The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data, including speech data, raises obvious security and privacy concerns. In particular, a user's speech data may be acquired and used with speech synthesis systems to produce high-quality speech utterances which reflect the same user's speaker identity. These utterances may then be used to attack speaker verification systems. One solution to mitigate these concerns …
Recent advances in deep learning have facilitated the design of speaker verification systems that directly input raw waveforms. For example, RawNet extracts speaker embeddings from raw waveforms, which simplifies the process pipeline and demonstrates competitive performance. In this study, we improve RawNet by scaling feature maps using various methods. The proposed mechanism utilizes a scale vector that adopts a sigmoid non-linear function. It refers to a vector with dimensionality equal to the number of filters in a given feature map. Using a scale vector, we propose to scale the feature map…
Most studies on speaker verification systems focus on long-duration utterances, which are composed of sufficient phonetic information. However, the performances of these systems are known to degrade when short-duration utterances are inputted due to the lack of phonetic information as compared to the long utterances. In this paper, we propose a method that compensates for the performance degradation of speaker verification for short utterances, referred to as "segment aggregation". The proposed method adopts an ensemble-based design to improve the stability and accuracy of speaker verification…
Although state-of-the-art parallel WaveNet has addressed the issue of real-time waveform generation, there remains problems. Firstly, due to the noisy input signal of the model, there is still a gap between the quality of generated and natural waveforms. Secondly, a parallel WaveNet is trained under a distillation framework, which makes it tedious to adapt a well trained model to a new speaker. To address these two problems, in this paper we propose an end-to-end adaptation method based on the generative adversarial network (GAN), which can reduce the computational cost for the training of new…
Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw audio samples directly. Differently from standard hand-crafted features such as MFCCs or FBANK, the raw waveform can potentially help neural networks discover better and more customized representations. The high-dimensional raw inputs, however, can make training significantly more challenging. This paper summarizes our recent efforts to develop a neural arc…
In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with linguistic and speaker characteristic features as auxiliary conditions, our method directly converts face images into speech waveforms under an end-to-end training framework. The linguistic features are extracted from lip movements using a lip-reading model, and the speaker characteristic features are predicted from face images using cross-modal learning with a pre-trained acoustic model. Since these two features are…
We propose Universal MelGAN, a vocoder that synthesizes high-fidelity speech in multiple domains. To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added multi-resolution spectrogram discriminators to sharpen the spectral resolution of the generated waveforms. This enables the model to generate realistic waveforms of multi-speakers, by alleviating the over-smoothing problem in the high frequency band of the large footprint model. Our structure generates signals close to ground-truth data without reducing the inference speed, by disc…
National Institute of Informatics（国立信息学研究所）；Massachusetts Institute of Technology（麻省理工学院）；University of Edinburgh（爱丁堡大学）
Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful representation learning framework that can discover discrete groups of features from a speech signal without supervision. Until now, the VQ-VAE architecture has previously modeled individual types of speech features, such as only phones or only F0. This paper introduces an important extension to VQ-VAE for learning F0-related suprasegmental information simultaneously along with traditional phone features.The proposed framework uses two encoders such that the F0 trajectory and speech waveform are both input to the system, therefo…
In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for recognizing their voice, which can vastly reduce the front-end computation and obtain state-of-the-art performance. However, these models do not consider the speaker's high-level behavioral features, such as intonation, indicating each speaker's universal style, rhythm, \textit{etc}. This paper presents a novel network that can handle the intonation information by com…
We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models. We extend two state-of-the-art PIT strategies. First, we look at the two-stage speaker separation and tracking algorithm based on frame level PIT (tPIT) and clustering, which was originally proposed for the STFT domain, and we adapt it to work with waveforms and over a learned latent space. Further, we propose an efficient clustering loss scalable to waveform models. Second, we extend a recently proposed auxiliary speaker-ID loss with a deep featur…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）；University of Edinburgh（爱丁堡大学）
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to vocoders and hence they are often called neural vocoders. The neural vocoder uses acoustic features as local condition parameters, and these parameters need to be accurately predicted by another acoustic model. However, it is not yet clear how to train this acoustic model, which is p…
Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform domains, like SampleRNN. This way, possible signal naturalness losses are avoided as intermediate acoustic representations are discarded. Another important dimension of study apart from naturalness is their adaptability to generate voice from new speakers that were unseen during training. In this paper we first propose the use of problem-agnostic speech embedding…
Self-Supervised Learning (SSL) has made great strides recently. SSL speech models achieve decent performance on a wide range of downstream tasks, suggesting that they extract different aspects of information from speech. However, how SSL models store various information in hidden representations without interfering is still poorly understood. Taking the recently successful SSL model, HuBERT, as an example, we explore how the SSL model processes and stores speaker information in the representation. We found that HuBERT stores speaker information in representations whose positions correspond to …
Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models employing full-band mel-spectrograms, an over-smoothing problem occurs as part of which non-sharp spectrograms are generated. To address this problem, we propose UnivNet, a neural vocoder that synthesizes high-fidelity waveforms in real time. Inspired by works in the field of voice activity detection, we added a multi-resolution spectrogram discriminator that empl…
National Institute of Informatics（国立信息学研究所）；The University of Edinburgh（爱丁堡大学）
An audiovisual speaker conversion method is presented for simultaneously transforming the facial expressions and voice of a source speaker into those of a target speaker. Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and for the generated target speaker to appear and sound natural. It uses three neural networks: a conversion network that fuses and transforms the facial and acoustic features, a waveform generation network that produces the waveform from both the converted facial and acoustic featur…
The short duration of an input utterance is one of the most critical threats that degrade the performance of speaker verification systems. This study aimed to develop an integrated text-independent speaker verification system that inputs utterances with short duration of 2 seconds or less. We propose an approach using a teacher-student learning framework for this goal, applied to short utterance compensation for the first time in our knowledge. The core concept of the proposed system is to conduct the compensation throughout the network that extracts the speaker embedding, mainly in phonetic-l…
National Institute of Informatics（国立信息学研究所）；University of Avignon（阿维尼翁大学）
Speaker anonymization aims to protect the privacy of speakers while preserving spoken linguistic information from speech. Current mainstream neural network speaker anonymization systems are complicated, containing an F0 extractor, speaker encoder, automatic speech recognition acoustic model (ASR AM), speech synthesis acoustic model and speech waveform generation model. Moreover, as an ASR AM is language-dependent, trained on English data, it is hard to adapt it into another language. In this paper, we propose a simpler self-supervised learning (SSL)-based method for language-independent speake…
Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information. However, current approaches normally either extract dirty content information with speaker information leaked in, or demand a large amount of annotated data for training. Besides, the quality of reconstructed waveform can be degraded by the mismatch between conversion model and vocoder. In this paper, we adopt the end-to-end framework of VITS for high-quality waveform reconstruction, and propose strategies for clean conten…
This paper presents the NWPU-ASLP speaker anonymization system for VoicePrivacy 2022 Challenge. Our submission does not involve additional Automatic Speaker Verification (ASV) model or x-vector pool. Our system consists of four modules, including feature extractor, acoustic model, anonymization module, and neural vocoder. First, the feature extractor extracts the Phonetic Posteriorgram (PPG) and pitch from the input speech signal. Then, we reserve a pseudo speaker ID from a speaker look-up table (LUT), which is subsequently fed into a speaker encoder to generate the pseudo speaker embedding th…
Northwestern Polytechnical University（西北工业大学）；School of Computer Science（计算机学院）
Speaker recognition is a popular topic in biometric authentication and many deep learning approaches have achieved extraordinary performances. However, it has been shown in both image and speech applications that deep neural networks are vulnerable to adversarial examples. In this study, we aim to exploit this weakness to perform targeted adversarial attacks against the x-vector based speaker recognition system. We propose to generate inaudible adversarial perturbations achieving targeted white-box attacks to speaker recognition system based on the psychoacoustic principle of frequency masking…
In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo speaker embedding system utilizes a queue to maintain a large set of negative examples. We show that better speaker embeddings can be learned by momentum contrastive learning. Next, alternative augmentation strategies are explored to normalize extrinsic speaker variabilities of two random segments from the same speech utterance. Specifically, augmentation in th…
The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time domain, which may produce suboptimal results because both time and frequency domains are important for speaker recognition. In this paper, we attempt to analyze the speech signal in both time and frequency domains and propose the time-frequency network~(TFN) for speaker recognition by extracting and fusing the features in the two domains. Based on the recent advan…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their performance. This was accomplished by the two parts teaching each other using both labeled and unlabeled data. This approach could significantly improve model performance within a single-speaker speech dataset, but only a slight increase could be gained in multi-speaker tasks. Furthermore, the model is still unable to handle unseen speakers. In this paper, we prese…
The Ohio State University（俄亥俄州立大学）；Facebook Reality Labs（Facebook现实实验室）；Facebook AI Research（Facebook人工智能研究院）；Tel-Aviv University（特拉维夫大学）
Most existing deep learning based binaural speaker separation systems focus on producing a monaural estimate for each of the target speakers, and thus do not preserve the interaural cues, which are crucial for human listeners to perform sound localization and lateralization. In this study, we address talker-independent binaural speaker separation with interaural cues preserved in the estimated binaural signals. Specifically, we extend a newly-developed gated recurrent neural network for monaural separation by additionally incorporating self-attention mechanisms and dense connectivity. We devel…
Single-channel speech separation in time domain and frequency domain has been widely studied for voice-driven applications over the past few years. Most of previous works assume known number of speakers in advance, however, which is not easily accessible through monaural mixture in practice. In this paper, we propose a novel model of single-channel multi-speaker separation by jointly learning the time-frequency feature and the unknown number of speakers. Specifically, our model integrates the time-domain convolution encoded feature map and the frequency-domain spectrogram by attention mechanis…
We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of naturalness in converted speech. Additionally, the lack of proper language features prevents these systems from accurately preserving language content after conversion. To address these issues, we devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. These discrete units provide duration information essential f…
We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform both tasks from the raw waveform. Wavesplit infers a set of source representations via clustering, which addresses the fundamental permutation problem of separation. For speech separation, our sequence-wide speaker representations provide a more robust separation of long, challenging recordings compared to prior work. Wavesplit redefines the state…
Institute of Computer Technology, Chinese Academic of Sciences（中国科学院计算技术研究所）；Peking University（北京大学）；University of Chinese Academic of Sciences（中国科学院大学）
Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention. Previous research mainly studied the attack to the vision-based system, such as fingerprint and face recognition. While the attack for speaker recognition has not been investigated yet, although it has been widely used in our daily life. In this paper, we attempt to fool the state-of-the-art speaker recognition model and present \textit{speaker recognition attacker}, a lightweight model to fool the deep speaker recognition model by…
Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel" hereafter) can greatly improve Automatic Speech Recognition (ASR) accuracy when optimized with an auxiliary loss utilizing a pre-trained ASR model encoder. In this paper, we develop a conformer-based waveform-domain neural AEC model inspired by the "TasNet" architecture. The model is trained by jointly optimizing Negative Scale-Invariant SNR (SISNR) and ASR …
Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware features are a possible solution to this problem. Most successful methods in both challenges focus on spoof-aware features, rather than focusing on a powerful classifier. In this paper we present a novel raw waveform based deep model for spoofing detection, which jointly acts as a feature extractor and classifier, thus allowing it to directly classify speech signa…
This paper presents a low-latency real-time (LLRT) non-parallel voice conversion (VC) framework based on cyclic variational autoencoder (CycleVAE) and multiband WaveRNN with data-driven linear prediction (MWDLP). CycleVAE is a robust non-parallel multispeaker spectral model, which utilizes a speaker-independent latent space and a speaker-dependent code to generate reconstructed/converted spectral features given the spectral features of an input speaker. On the other hand, MWDLP is an efficient and a high-quality neural vocoder that can handle multispeaker data and generate speech waveform for …
In this paper, we propose an innovative approach to perform speaker recognition by fusing two recently introduced deep neural networks (DNNs) namely - SincNet and X-Vector. The idea behind using SincNet filters on the raw speech waveform is to extract more distinguishing frequency-related features in the initial convolution layers of the CNN architecture. X-Vectors are used to take advantage of the fact that this embedding is an efficient method to churn out fixed dimension features from variable length speech utterances, something which is challenging in plain CNN techniques, making it effici…
This paper introduces RawBoost, a data boosting and augmentation method for the design of more reliable spoofing detection solutions which operate directly upon raw waveform inputs. While RawBoost requires no additional data sources, e.g. noise recordings or impulse responses and is data, application and model agnostic, it is designed for telephony scenarios. Based upon the combination of linear and non-linear convolutive noise, impulsive signal-dependent additive noise and stationary signal-independent additive noise, RawBoost models nuisance variability stemming from, e.g., encoding, transmi…
Lyrebird AI（Lyrebird人工智能公司）；Mila（米拉研究所）；University of Montreal（蒙特利尔大学）；CIFAR（加拿大高等研究院）
Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques. Subjective evaluation metric (Mean Opinion Score, or MOS) shows the effectiveness of the proposed approach for high quality mel-spectrogram inversion. To establish the generality of the proposed techniques, we show qualitative results of our model in speech synthesis, m…
Shanghai University（上海大学）；Shanghai Institute for Advanced Communication and Data Science (SICS)（上海先进通信与数据科学研究院（SICS））
In recent years, synthetic speech generated by advanced text-to-speech (TTS) and voice conversion (VC) systems has caused great harms to automatic speaker verification (ASV) systems, urging us to design a synthetic speech detection system to protect ASV systems. In this paper, we propose a new speech anti-spoofing model named ResWavegram-Resnet (RW-Resnet). The model contains two parts, Conv1D Resblocks and backbone Resnet34. The Conv1D Resblock is based on the Conv1D block with a residual connection. For the first part, we use the raw waveform as input and feed it to the stacked Conv1D Resblo…
