VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis

Achieving nuanced and accurate emulation of human voice has been a longstanding goal in artificial intelligence. Although significant progress has been made in recent years, the mainstream of speech synthesis models still relies on supervised speaker modeling and explicit reference utterances. However, there are many aspects of human voice, such as emotion, intonation, and speaking style, for which it is hard to obtain accurate labels. In this paper, we propose VoxGenesis, a novel unsupervised speech synthesis framework that can discover a latent speaker manifold and meaningful voice editing directions without supervision. VoxGenesis is conceptually simple. Instead of mapping speech features to waveforms deterministically, VoxGenesis transforms a Gaussian distribution into speech distributions conditioned and aligned by semantic tokens. This forces the model to learn a speaker distribution disentangled from the semantic content. During the inference, sampling from the Gaussian distribution enables the creation of novel speakers with distinct characteristics. More importantly, the exploration of latent space uncovers human-interpretable directions associated with specific speaker characteristics such as gender attributes, pitch, tone, and emotion, allowing for voice editing by manipulating the latent codes along these identified directions. We conduct extensive experiments to evaluate the proposed VoxGenesis using both subjective and objective metrics, finding that it produces significantly more diverse and realistic speakers with distinct characteristics than the previous approaches. We also show that latent space manipulation produces consistent and human-identifiable effects that are not detrimental to the speech quality, which was not possible with previous approaches. Audio samples of VoxGenesis can be found at: \url{https://bit.ly/VoxGenesis}.

Phonetic-aware speaker embedding for far-field speaker verification

When a speaker verification (SV) system operates far from the sound sourced, significant challenges arise due to the interference of noise and reverberation. Studies have shown that incorporating phonetic information into speaker embedding can improve the performance of text-independent SV. Inspired by this observation, we propose a joint-training speech recognition and speaker recognition (JTSS) framework to exploit phonetic content for far-field SV. The framework encourages speaker embeddings to preserve phonetic information by matching the frame-based feature maps of a speaker embedding network with wav2vec's vectors. The intuition is that phonetic information can preserve low-level acoustic dynamics with speaker information and thus partly compensate for the degradation due to noise and reverberation. Results show that the proposed framework outperforms the standard speaker embedding on the VOiCES Challenge 2019 evaluation set and the VoxCeleb1 test set. This indicates that leveraging phonetic information under far-field conditions is effective for learning robust speaker representations.

Contrastive Speaker Embedding With Sequential Disentanglement

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker identity but also linguistic content. In this paper, we propose a contrastive learning framework with sequential disentanglement to remove linguistic content by incorporating a disentangled sequential variational autoencoder (DSVAE) into the conventional SimCLR framework. The DSVAE aims to disentangle speaker factors from content factors in an embedding space so that only the speaker factors are used for constructing a contrastive loss objective. Because content factors have been removed from the contrastive learning, the resulting speaker embeddings will be content-invariant. Experimental results on VoxCeleb1-test show that the proposed method consistently outperforms SimCLR. This suggests that applying sequential disentanglement is beneficial to learning speaker-discriminative embeddings.

Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification

Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data. Performing data augmentation on raw waveforms, such as adding noise or reverberation, plays a pivotal role in achieving promising results in SV. Data augmentation, however, demands meticulous calibration to ensure intact speaker-specific information, which is difficult to achieve without speaker labels. To address this issue, we introduce a novel framework by incorporating clean and augmented segments into the contrastive training pipeline. The clean segments are repurposed to pair with noisy segments to form additional positive and negative pairs. Moreover, the contrastive loss is weighted to increase the difference between the clean and augmented embeddings of different speakers. Experimental results on Voxceleb1 suggest that the proposed framework can achieve a remarkable 19% improvement over the conventional methods, and it surpasses many existing state-of-the-art techniques.

Progression-Guided Temporal Action Detection in Videos

We present a novel framework, Action Progression Network (APN), for temporal action detection (TAD) in videos. The framework locates actions in videos by detecting the action evolution process. To encode the action evolution, we quantify a complete action process into 101 ordered stages (0\%, 1\%, ..., 100\%), referred to as action progressions. We then train a neural network to recognize the action progressions. The framework detects action boundaries by detecting complete action processes in the videos, e.g., a video segment with detected action progressions closely follow the sequence 0\%, 1\%, ..., 100\%. The framework offers three major advantages: (1) Our neural networks are trained end-to-end, contrasting conventional methods that optimize modules separately; (2) The APN is trained using action frames exclusively, enabling models to be trained on action classification datasets and robust to videos with temporal background styles differing from those in training; (3) Our framework effectively avoids detecting incomplete actions and excels in detecting long-lasting actions due to the fine-grained and explicit encoding of the temporal structure of actions. Leveraging these advantages, the APN achieves competitive performance and significantly surpasses its counterparts in detecting long-lasting actions. With an IoU threshold of 0.5, the APN achieves a mean Average Precision (mAP) of 58.3\% on the THUMOS14 dataset and 98.9\% mAP on the DFMAD70 dataset.

Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations

Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition (ASR) and proved to be extremely useful in low label-resource settings. However, the success of SSL models has yet to transfer to utterance-level tasks such as speaker, emotion, and language recognition, which still require supervised fine-tuning of the SSL models to obtain good performance. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective for these tasks. Inspired by how HuBERT uses clustering to discover hidden acoustic units, we formulate a factor analysis (FA) model that uses the discovered hidden acoustic units to align the SSL features. The underlying utterance-level representations are disentangled from the content of speech using probabilistic inference on the aligned features. Furthermore, the variational lower bound derived from the FA model provides an utterance-level objective, allowing error gradients to be backpropagated to the Transformer layers to learn highly discriminative acoustic units. When used in conjunction with HuBERT's masked prediction training, our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.

Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome these challenges, we propose a contrastive learning SV framework incorporating an additive angular margin into the supervised contrastive loss. The margin improves the speaker representation's discrimination ability. We introduce a class-aware attention mechanism through which hard negative samples contribute less significantly to the supervised contrastive loss. We also employed a gradient-based multi-objective optimization approach to balance the classification and contrastive loss. Experimental results on CN-Celeb and Voxceleb1 show that this new learning objective can cause the encoder to find an embedding space that exhibits great speaker discrimination across languages.

Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning objective to learn a speaker embedding space by effectively leveraging the label information in the training data. In such a space, utterance pairs spoken by the same or similar speakers will stay close, while utterance pairs spoken by different speakers will be far apart. For each training speaker, we perform random data augmentation on their utterances to form positive pairs, and utterances from different speakers form negative pairs. To maximize speaker separability in the embedding space, we incorporate the additive angular-margin loss into the contrastive learning objective. Experimental results on CN-Celeb show that this new learning objective can cause ECAPA-TDNN to find an embedding space that exhibits great speaker discrimination. The contrastive learning objective is easy to implement, and we provide PyTorch code at https://github.com/shanmon110/AAMSupCon.