Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during decision-making, resulting in suboptimal performance. Although multi-model fusion (MMF) can mitigate some of these issues, redundancy in learned representations may limits improvements. To this end, we propose an adversarial complementary representation learning (ACoRL) framework that enables newly trained models to avoid previously acquired knowledge, allowing each individual component model to learn maximally distinct, complementary representations. We make three detailed explanations of why this works and experimental results demonstrate that our method more efficiently improves performance compared to traditional MMF. Furthermore, attribution analysis validates the model trained under ACoRL acquires more complementary knowledge, highlighting the efficacy of our approach in enhancing efficiency and robustness across tasks.

Retrieval-Augmented Audio Deepfake Detection

With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most deepfake (DF) detection methods rely solely on the fuzzy knowledge learned by a single model, resulting in performance bottlenecks and transparency issues. Inspired by retrieval-augmented generation (RAG), we propose a retrieval-augmented detection (RAD) framework that augments test samples with similar retrieved samples for enhanced detection. We also extend the multi-fusion attentive classifier to integrate it with our proposed RAD framework. Extensive experiments show the superior performance of the proposed RAD framework over baseline methods, achieving state-of-the-art results on the ASVspoof 2021 DF set and competitive results on the 2019 and 2021 LA sets. Further sample analysis indicates that the retriever consistently retrieves samples mostly from the same speaker with acoustic characteristics highly consistent with the query audio, thereby improving detection performance.

VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration speech signals. We use two guided diffusion models, the built-in and the external speaker embedding (SE) guided diffusion model, both of which utilize a diffusion model-based sample generator that leverages SE guidance to augment the speech features based on a short utterance. Extensive experimental results on the VoxCeleb1 dataset show that our method outperforms the baseline, with relative improvements in equal error rate (EER) of 46.1%, 35.7%, 10.4%, and 5.7% for the short utterance conditions of 0.5, 1.0, 1.5, and 2.0 seconds, respectively.

SVVAD: Personal Voice Activity Detection for Speaker Verification

Voice activity detection (VAD) improves the performance of speaker verification (SV) by preserving speech segments and attenuating the effects of non-speech. However, this scheme is not ideal: (1) it fails in noisy environments or multi-speaker conversations; (2) it is trained based on inaccurate non-SV sensitive labels. To address this, we propose a speaker verification-based voice activity detection (SVVAD) framework that can adapt the speech features according to which are most informative for SV. To achieve this, we introduce a label-free training method with triplet-like losses that completely avoids the performance degradation of SV due to incorrect labeling. Extensive experiments show that SVVAD significantly outperforms the baseline in terms of equal error rate (EER) under conditions where other speakers are mixed at different ratios. Moreover, the decision boundaries reveal the importance of the different parts of speech, which are largely consistent with human judgments.

Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification

Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major breakthroughs in computer vision. Despite promising results, the technique has not been well applied to audio and signal processing. Due to the variable duration of audio signals, it has its own unique way of modeling. In this work, we propose feature-rich audio model inversion (FRAMI), a data-free knowledge distillation framework for general sound classification tasks. It first generates high-quality and feature-rich Mel-spectrograms through a feature-invariant contrastive loss. Then, the hidden states before and after the statistics pooling layer are reused when knowledge distillation is performed on these feature-rich samples. Experimental results on the Urbansound8k, ESC-50, and audioMNIST datasets demonstrate that FRAMI can generate feature-rich samples. Meanwhile, the accuracy of the student model is further improved by reusing the hidden state and significantly outperforms the baseline method.

SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning

Estimating age from a single speech is a classic and challenging topic. Although Label Distribution Learning (LDL) can represent adjacent indistinguishable ages well, the uncertainty of the age estimate for each utterance varies from person to person, i.e., the variance of the age distribution is different. To address this issue, we propose selective variance label distribution learning (SVLDL) method to adapt the variance of different age distributions. Furthermore, the model uses WavLM as the speech feature extractor and adds the auxiliary task of gender recognition to further improve the performance. Two tricks are applied on the loss function to enhance the robustness of the age estimation and improve the quality of the fitted age distribution. Extensive experiments show that the model achieves state-of-the-art performance on all aspects of the NIST SRE08-10 and a real-world datasets.

SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning

Speech emotion recognition (SER) has many challenges, but one of the main challenges is that each framework does not have a unified standard. In this paper, we propose SpeechEQ, a framework for unifying SER tasks based on a multi-scale unified metric. This metric can be trained by Multitask Learning (MTL), which includes two emotion recognition tasks of Emotion States Category (EIS) and Emotion Intensity Scale (EIS), and two auxiliary tasks of phoneme recognition and gender recognition. For this framework, we build a Mandarin SER dataset - SpeechEQ Dataset (SEQD). We conducted experiments on the public CASIA and ESD datasets in Mandarin, which exhibit that our method outperforms baseline methods by a relatively large margin, yielding 8.0\% and 6.5\% improvement in accuracy respectively. Additional experiments on IEMOCAP with four emotion categories (i.e., angry, happy, sad, and neutral) also show the proposed method achieves a state-of-the-art of both weighted accuracy (WA) of 78.16% and unweighted accuracy (UA) of 77.47%.