29 accepted papers
In speech deepfake detection (SDD), data augmentation (DA) is commonly used to improve model generalization across varied speech conditions and spoofing attacks. However, during training, the backpropagated gradients from original and augmented inputs may misalign, which can result in conflicting pa…
Speech codecs serve as bridges between continuous speech signals and large language models, yet face an inherent conflict between acoustic fidelity and semantic preservation. To mitigate this conflict, prevailing methods augment acoustic codecs with complex semantic supervision. We explore the oppos…
Protecting speaker identity is crucial for online voice applications, yet streaming speaker anonymization (SA) remains underexplored. Recent research has demonstrated that neural audio codec (NAC) provides superior speaker feature disentanglement and linguistic fidelity. NAC can also be used with ca…
Recent works suggest that decoupling the information of non-target speakers from that of the target speaker in knowledge distillation (KD) and subsequently emphasizing the former can lead to significant performance improvement. However, a well-trained teacher model typically produces almost zero non…
Previous fake speech datasets were constructed from a defender’s perspective to develop countermeasure (CM) systems without considering diverse motivations of attackers. To better align with real-life scenarios, we created LlamaPartialSpoof, a 130-hour dataset that contains both fully and partially…
In contrast to text-independent speaker verification, which has received significant attention from researchers and has many competitions dedicated to it, text-dependent speaker verification (TdSV) has been less explored recently. The TdSV Challenge 2024 was organized to analyze and explore novel me…
Conventional copy-paste augmentations generate new training instances by concatenating existing utterances to increase the amount of data for neural network training. However, the direct application of copy-paste augmentation for anti-spoofing is problematic. This paper refines the copy-paste augmen…
Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the conventional label-level KD overlooks the significant knowledge from n…
Speaker verification is hampered by background noise, particularly at extremely low Signal-to-Noise Ratio (SNR) under 0 dB. It is difficult to suppress noise without introducing unwanted artifacts, which adversely affects speaker verification. We proposed the mechanism called Gradient Weighting (Gra…
Voice anonymization refers to the goal of suppressing personally identifiable voice attributes in speech. State-of-the-art models based on the voice conversion framework accomplish this goal by replacing the voice attributes of the speaker with those of a pseudo-speaker. This paper proposes to explo…
Speaker recognition technologies have been successfully applied in diverse domains, benefiting from the advance of deep learning. Nevertheless, current efforts are still subject to the lack of labeled data. Such issues have been attempted in computer vision, through semi-supervised learning (SSL) th…
Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is mo…
For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with t…
Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the same neural network. This paper aims to incorporate the uncertainty estimate produced in the xi-vector network front-end w…
Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. As synthetic speech exhibits local and global artifacts compared to natural speech, incorporating local-global dependency would lead to better anti-spoofing performance. To this end, we propose the Rawformer that levera…
Automatic speaker verification (ASV) suffers from performance degradation in noisy environments. To solve this problem, we propose the noise-disentanglement metric learning to reduce the speaker-irrelevant noisy components and build a noise-invariant embedding space. Specifically, the disentanglemen…
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…
In self-supervised speaker verification, the quality of pseudo labels determines the upper bound of its performance and it is not uncommon to end up with massive amount of unreliable pseudo labels. We observe that the complementary information in different modalities ensures a robust supervisory sig…
Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance. However, noisy samples (i.e., with wrong labels) in the training…
In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However,…
Automatic speaker verification (ASV) faces domain shift caused by the mismatch of intrinsic and extrinsic factors such as recording device and speaking style in real-world applications, which leads to unsatisfactory performance. To this end, we propose the meta generalized transformation via meta-le…
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local frequency region. In addition, the performance of such systems…
In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn’t always benefit from pseudo labels due to their unreliability. In this work, we observe that a speaker recognition network tends to mod…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
The principal way of performing user profiling is to investigate accumulated social media data. However, the problem of information asymmetry generally exists in user generated contents since users post multi-modal contents in social media freely. In this paper, we propose a novel text-image coopera…
Automatic speaker verification (ASV) has been successfully deployed for identity recognition. With increasing use of ASV technology in real-world applications, channel mismatch caused by the recording devices and environments severely degrade its performance, especially in the case of unseen channel…
Variable-resolution processing aims to improve the feature representation ability by enlarging the local discriminative details. In previous anti-spoofing studies, different phones and frequency regions were both proven to have various levels of sensitivity to replay distortion. In this paper, an ad…
This paper proposes a generalized framework for domain adaptation of Probabilistic Linear Discriminant Analysis (PLDA) in speaker recognition. It not only includes several existing supervised and unsupervised domain adaptation methods but also makes possible more flexible usage of available data in…
State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the availability of a large collection of labeled training data. In pra…