NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose NaturalSpeech 3, a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt. With this factorization design, NaturalSpeech 3 can effectively and efficiently model the intricate speech with disentangled subspaces in a divide-and-conquer way. Experiments show that NaturalSpeech 3 outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility. Furthermore, we achieve better performance by scaling to 1B parameters and 200K hours of training data.

SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion

In this study, we present SingVisio, an interactive visual analysis system that aims to explain the diffusion model used in singing voice conversion. SingVisio provides a visual display of the generation process in diffusion models, showcasing the step-by-step denoising of the noisy spectrum and its transformation into a clean spectrum that captures the desired singer's timbre. The system also facilitates side-by-side comparisons of different conditions, such as source content, melody, and target timbre, highlighting the impact of these conditions on the diffusion generation process and resulting conversions. Through comprehensive evaluations, SingVisio demonstrates its effectiveness in terms of system design, functionality, explainability, and user-friendliness. It offers users of various backgrounds valuable learning experiences and insights into the diffusion model for singing voice conversion.

CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing

There has been a long-standing quest for a unified audio-visual-text model to enable various multimodal understanding tasks, which mimics the listening, seeing and reading process of human beings. Humans tends to represent knowledge using two separate systems: one for representing verbal (textual) information and one for representing non-verbal (visual and auditory) information. These two systems can operate independently but can also interact with each other. Motivated by this understanding of human cognition, in this paper, we introduce CoAVT -- a novel cognition-inspired Correlated Audio-Visual-Text pre-training model to connect the three modalities. It contains a joint audio-visual encoder that learns to encode audio-visual synchronization information together with the audio and visual content for non-verbal information, and a text encoder to handle textual input for verbal information. To bridge the gap between modalities, CoAVT employs a query encoder, which contains a set of learnable query embeddings, and extracts the most informative audiovisual features of the corresponding text. Additionally, to leverage the correspondences between audio and vision with language respectively, we also establish the audio-text and visual-text bi-modal alignments upon the foundational audiovisual-text tri-modal alignment to enhance the multimodal representation learning. Finally, we jointly optimize CoAVT model with three multimodal objectives: contrastive loss, matching loss and language modeling loss. Extensive experiments show that CoAVT can learn strong multimodal correlations and be generalized to various downstream tasks. CoAVT establishes new state-of-the-art performance on text-video retrieval task on AudioCaps for both zero-shot and fine-tuning settings, audio-visual event classification and audio-visual retrieval tasks on AudioSet and VGGSound.

Amphion: An Open-Source Audio, Music and Speech Generation Toolkit

Amphion is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development. Amphion offers a unique feature: visualizations of classic models or architectures. We believe that these visualizations are beneficial for junior researchers and engineers who wish to gain a better understanding of the model. The North-Star objective of Amphion is to offer a platform for studying the conversion of any inputs into general audio. Amphion is designed to support individual generation tasks. In addition to the specific generation tasks, Amphion also includes several vocoders and evaluation metrics. A vocoder is an important module for producing high-quality audio signals, while evaluation metrics are critical for ensuring consistent metrics in generation tasks. In this paper, we provide a high-level overview of Amphion.

Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder

Generative Adversarial Network (GAN) based vocoders are superior in inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator to promote GAN-based vocoders. Most existing time-frequency-representation-based discriminators are rooted in Short-Time Fourier Transform (STFT), whose time-frequency resolution in a spectrogram is fixed, making it incompatible with signals like singing voices that require flexible attention for different frequency bands. Motivated by that, our study utilizes the Constant-Q Transform (CQT), which owns dynamic resolution among frequencies, contributing to a better modeling ability in pitch accuracy and harmonic tracking. Specifically, we propose a Multi-Scale Sub-Band CQT (MS-SB-CQT) Discriminator, which operates on the CQT spectrogram at multiple scales and performs sub-band processing according to different octaves. Experiments conducted on both speech and singing voices confirm the effectiveness of our proposed method. Moreover, we also verified that the CQT-based and the STFT-based discriminators could be complementary under joint training. Specifically, enhanced by the proposed MS-SB-CQT and the existing MS-STFT Discriminators, the MOS of HiFi-GAN can be boosted from 3.27 to 3.87 for seen singers and from 3.40 to 3.78 for unseen singers.

Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion

Singing voice conversion (SVC) is a technique to enable an arbitrary singer to sing an arbitrary song. To achieve that, it is important to obtain speaker-agnostic representations from source audio, which is a challenging task. A common solution is to extract content-based features (e.g., PPGs) from a pretrained acoustic model. However, the choices for acoustic models are vast and varied. It is yet to be explored what characteristics of content features from different acoustic models are, and whether integrating multiple content features can help each other. Motivated by that, this study investigates three distinct content features, sourcing from WeNet, Whisper, and ContentVec, respectively. We explore their complementary roles in intelligibility, prosody, and conversion similarity for SVC. By integrating the multiple content features with a diffusion-based SVC model, our SVC system achieves superior conversion performance on both objective and subjective evaluation in comparison to a single source of content features. Our demo page and code can be available https://www.zhangxueyao.com/data/MultipleContentsSVC/index.html.

An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verification

Deep Learning has advanced Automatic Speaker Verification (ASV) in the past few years. Although it is known that deep learning-based ASV systems are vulnerable to adversarial examples in digital access, there are few studies on adversarial attacks in the context of physical access, where a replay process (i.e., over the air) is involved. An over-the-air attack involves a loudspeaker, a microphone, and a replaying environment that impacts the movement of the sound wave. Our initial experiment confirms that the replay process impacts the effectiveness of the over-the-air attack performance. This study performs an initial investigation towards utilizing a neural replay simulator to improve over-the-air adversarial attack robustness. This is achieved by using a neural waveform synthesizer to simulate the replay process when estimating the adversarial perturbations. Experiments conducted on the ASVspoof2019 dataset confirm that the neural replay simulator can considerably increase the success rates of over-the-air adversarial attacks. This raises the concern for adversarial attacks on speaker verification in physical access applications.

Audio compression-assisted feature extraction for voice replay attack detection

Replay attack is one of the most effective and simplest voice spoofing attacks. Detecting replay attacks is challenging, according to the Automatic Speaker Verification Spoofing and Countermeasures Challenge 2021 (ASVspoof 2021), because they involve a loudspeaker, a microphone, and acoustic conditions (e.g., background noise). One obstacle to detecting replay attacks is finding robust feature representations that reflect the channel noise information added to the replayed speech. This study proposes a feature extraction approach that uses audio compression for assistance. Audio compression compresses audio to preserve content and speaker information for transmission. The missed information after decompression is expected to contain content- and speaker-independent information (e.g., channel noise added during the replay process). We conducted a comprehensive experiment with a few data augmentation techniques and 3 classifiers on the ASVspoof 2021 physical access (PA) set and confirmed the effectiveness of the proposed feature extraction approach. To the best of our knowledge, the proposed approach achieves the lowest EER at 22.71% on the ASVspoof 2021 PA evaluation set.

AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification

It is known that deep neural networks are vulnerable to adversarial attacks. Although Automatic Speaker Verification (ASV) built on top of deep neural networks exhibits robust performance in controlled scenarios, many studies confirm that ASV is vulnerable to adversarial attacks. The lack of a standard dataset is a bottleneck for further research, especially reproducible research. In this study, we developed an open-source adversarial attack dataset for speaker verification research. As an initial step, we focused on the over-the-air attack. An over-the-air adversarial attack involves a perturbation generation algorithm, a loudspeaker, a microphone, and an acoustic environment. The variations in the recording configurations make it very challenging to reproduce previous research. The AdvSV dataset is constructed using the Voxceleb1 Verification test set as its foundation. This dataset employs representative ASV models subjected to adversarial attacks and records adversarial samples to simulate over-the-air attack settings. The scope of the dataset can be easily extended to include more types of adversarial attacks. The dataset will be released to the public under the CC-BY license. In addition, we also provide a detection baseline for reproducible research.