Quantifying Source Speaker Leakage in One-to-One Voice Conversion

Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a HiFi-GAN vocoder, we compare information leakage for a range speaker characteristics; assuming a "worst-case" white-box scenario, we quantify our confidence to perform inference and narrow the pool of likely source speakers, reinforcing the regulatory obligation and moral duty that providers of synthetic voices have to ensure the privacy of their speakers' data.

FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge in this task is generalizing models to detect unseen, out-of-distribution (OOD) attacks. Although existing approaches have shown promising results, they inherently suffer from overconfidence issues due to the usage of softmax for classification, which can produce unreliable predictions when encountering unpredictable spoofing attempts. To deal with this limitation, we propose a novel framework called fake audio detection with evidential learning (FADEL). By modeling class probabilities with a Dirichlet distribution, FADEL incorporates model uncertainty into its predictions, thereby leading to more robust performance in OOD scenarios. Experimental results on the ASVspoof2019 Logical Access (LA) and ASVspoof2021 LA datasets indicate that the proposed method significantly improves the performance of baseline models. Furthermore, we demonstrate the validity of uncertainty estimation by analyzing a strong correlation between average uncertainty and equal error rate (EER) across different spoofing algorithms.

Giving AI a voice: how does AI think it should be treated?

With the astounding progress in (generative) artificial intelligence (AI), there has been significant public discourse regarding regulation and ethics of the technology. Is it sufficient when humans discuss this with other humans? Or, given that AI is increasingly becoming a viable source of inspiration for people (and let alone the hypothetical possibility that the technology may at some point become "artificial general intelligence" and/or develop consciousness), should AI not join the discourse? There are new questions and angles that AI brings to the table that we might not have considered before - so let us make the key subject of this book an active participant. This chapter therefore includes a brief human-AI conversation on the topic of AI rights and ethics.

Speaker Fuzzy Fingerprints: Benchmarking Text-Based Identification in Multiparty Dialogues

Speaker identification using voice recordings leverages unique acoustic features, but this approach fails when only textual data is available. Few approaches have attempted to tackle the problem of identifying speakers solely from text, and the existing ones have primarily relied on traditional methods. In this work, we explore the use of fuzzy fingerprints from large pre-trained models to improve text-based speaker identification. We integrate speaker-specific tokens and context-aware modeling, demonstrating that conversational context significantly boosts accuracy, reaching 70.6% on the Friends dataset and 67.7% on the Big Bang Theory dataset. Additionally, we show that fuzzy fingerprints can approximate full fine-tuning performance with fewer hidden units, offering improved interpretability. Finally, we analyze ambiguous utterances and propose a mechanism to detect speaker-agnostic lines. Our findings highlight key challenges and provide insights for future improvements in text-based speaker identification.

Collective Learning Mechanism based Optimal Transport Generative Adversarial Network for Non-parallel Voice Conversion

After demonstrating significant success in image synthesis, Generative Adversarial Network (GAN) models have likewise made significant progress in the field of speech synthesis, leveraging their capacity to adapt the precise distribution of target data through adversarial learning processes. Notably, in the realm of State-Of-The-Art (SOTA) GAN-based Voice Conversion (VC) models, there exists a substantial disparity in naturalness between real and GAN-generated speech samples. Furthermore, while many GAN models currently operate on a single generator discriminator learning approach, optimizing target data distribution is more effectively achievable through a single generator multi-discriminator learning scheme. Hence, this study introduces a novel GAN model named Collective Learning Mechanism-based Optimal Transport GAN (CLOT-GAN) model, incorporating multiple discriminators, including the Deep Convolutional Neural Network (DCNN) model, Vision Transformer (ViT), and conformer. The objective of integrating various discriminators lies in their ability to comprehend the formant distribution of mel-spectrograms, facilitated by a collective learning mechanism. Simultaneously, the inclusion of Optimal Transport (OT) loss aims to precisely bridge the gap between the source and target data distribution, employing the principles of OT theory. The experimental validation on VCC 2018, VCTK, and CMU-Arctic datasets confirms that the CLOT-GAN-VC model outperforms existing VC models in objective and subjective assessments.

Voice Conversion with Diverse Intonation using Conditional Variational Auto-Encoder

Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different intonations, conventional voice conversion models were limited to producing only one result per source input. To overcome this limitation, we propose a novel approach for voice conversion with diverse intonations using conditional variational autoencoder (CVAE). Experiments have shown that the speaker's style feature can be mapped into a latent space with Gaussian distribution. We have also been able to convert voices with more diverse intonation by making the posterior of the latent space more complex with inverse autoregressive flow (IAF). As a result, the converted voice not only has a diversity of intonations, but also has better sound quality than the model without CVAE.

Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations

The advancement of AI systems for mental health support is hindered by limited access to therapeutic conversation data, particularly for trauma treatment. We present Thousand Voices of Trauma, a synthetic benchmark dataset of 3,000 therapy conversations based on Prolonged Exposure therapy protocols for Post-traumatic Stress Disorder (PTSD). The dataset comprises 500 unique cases, each explored through six conversational perspectives that mirror the progression of therapy from initial anxiety to peak distress to emotional processing. We incorporated diverse demographic profiles (ages 18-80, M=49.3, 49.4% male, 44.4% female, 6.2% non-binary), 20 trauma types, and 10 trauma-related behaviors using deterministic and probabilistic generation methods. Analysis reveals realistic distributions of trauma types (witnessing violence 10.6%, bullying 10.2%) and symptoms (nightmares 23.4%, substance abuse 20.8%). Clinical experts validated the dataset's therapeutic fidelity, highlighting its emotional depth while suggesting refinements for greater authenticity. We also developed an emotional trajectory benchmark with standardized metrics for evaluating model responses. This privacy-preserving dataset addresses critical gaps in trauma-focused mental health data, offering a valuable resource for advancing both patient-facing applications and clinician training tools.

Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy

Generalizability, the capacity of a robust model to perform effectively on unseen data, is crucial for audio deepfake detection due to the rapid evolution of text-to-speech (TTS) and voice conversion (VC) technologies. A promising approach to differentiate between bonafide and spoof samples lies in identifying intrinsic disparities to enhance model generalizability. From an information-theoretic perspective, we hypothesize the information content is one of the intrinsic differences: bonafide sample represents a dense, information-rich sampling of the real world, whereas spoof sample is typically derived from lower-dimensional, less informative representations. To implement this, we introduce frame-level latent information entropy detector(f-InfoED), a framework that extracts distinctive information entropy from latent representations at the frame level to identify audio deepfakes. Furthermore, we present AdaLAM, which extends large pre-trained audio models with trainable adapters for enhanced feature extraction. To facilitate comprehensive evaluation, the audio deepfake forensics 2024 (ADFF 2024) dataset was built by the latest TTS and VC methods. Extensive experiments demonstrate that our proposed approach achieves state-of-the-art performance and exhibits remarkable generalization capabilities. Further analytical studies confirms the efficacy of AdaLAM in extracting discriminative audio features and f-InfoED in leveraging latent entropy information for more generalized deepfake detection.

Will AI shape the way we speak? The emerging sociolinguistic influence of synthetic voices

The growing prevalence of conversational voice interfaces, powered by developments in both speech and language technologies, raises important questions about their influence on human communication. While written communication can signal identity through lexical and stylistic choices, voice-based interactions inherently amplify socioindexical elements - such as accent, intonation, and speech style - which more prominently convey social identity and group affiliation. There is evidence that even passive media such as television is likely to influence the audience's linguistic patterns. Unlike passive media, conversational AI is interactive, creating a more immersive and reciprocal dynamic that holds a greater potential to impact how individuals speak in everyday interactions. Such heightened influence can be expected to arise from phenomena such as acoustic-prosodic entrainment and linguistic accommodation, which occur naturally during interaction and enable users to adapt their speech patterns in response to the system. While this phenomenon is still emerging, its potential societal impact could provide organisations, movements, and brands with a subtle yet powerful avenue for shaping and controlling public perception and social identity. We argue that the socioindexical influence of AI-generated speech warrants attention and should become a focus of interdisciplinary research, leveraging new and existing methodologies and technologies to better understand its implications.

Mitigating Timbre Leakage with Universal Semantic Mapping Residual Block for Voice Conversion

Voice conversion (VC) transforms source speech into a target voice by preserving the content. However, timbre information from the source speaker is inherently embedded in the content representations, causing significant timbre leakage and reducing similarity to the target speaker. To address this, we introduce a residual block to a content extractor. The residual block consists of two weighted branches: 1) universal semantic dictionary based Content Feature Re-expression (CFR) module, supplying timbre-free content representation. 2) skip connection to the original content layer, providing complementary fine-grained information. In the CFR module, each dictionary entry in the universal semantic dictionary represents a phoneme class, computed statistically using speech from multiple speakers, creating a stable, speaker-independent semantic set. We introduce a CFR method to obtain timbre-free content representations by expressing each content frame as a weighted linear combination of dictionary entries using corresponding phoneme posteriors as weights. Extensive experiments across various VC frameworks demonstrate that our approach effectively mitigates timbre leakage and significantly improves similarity to the target speaker.