Bias in speech emotion recognition (SER) systems often stems from spurious correlations between speaker characteristics and emotional labels, leading to unfair predictions across demographic groups. Many existing debiasing methods require model-specific changes or demographic annotations, limiting their practical use. We present CO-VADA, a Confidence-Oriented Voice Augmentation Debiasing Approach that mitigates bias without modifying model architecture or relying on demographic information. CO-VADA identifies training samples that reflect bias patterns present in the training data and then applies voice conversion to alter irrelevant attributes and generate samples. These augmented samples introduce speaker variations that differ from dominant patterns in the data, guiding the model to focus more on emotion-relevant features. Our framework is compatible with various SER models and voice conversion tools, making it a scalable and practical solution for improving fairness in SER systems.
We introduce LinearVC, a simple voice conversion method that sheds light on the structure of self-supervised representations. First, we show that simple linear transformations of self-supervised features effectively convert voices. Next, we probe the geometry of the feature space by constraining the set of allowed transformations. We find that just rotating the features is sufficient for high-quality voice conversion. This suggests that content information is embedded in a low-dimensional subspace which can be linearly transformed to produce a target voice. To validate this hypothesis, we finally propose a method that explicitly factorizes content and speaker information using singular value decomposition; the resulting linear projection with a rank of just 100 gives competitive conversion results. Our work has implications for both practical voice conversion and a broader understanding of self-supervised speech representations. Samples and code: https://www.kamperh.com/linearvc/.
This paper introduces Factorized MKL-VC, a training-free modification for kNN-VC pipeline. In contrast with original pipeline, our algorithm performs high quality any-to-any cross-lingual voice conversion with only 5 second of reference audio. MKL-VC replaces kNN regression with a factorized optimal transport map in WavLM embedding subspaces, derived from Monge-Kantorovich Linear solution. Factorization addresses non-uniform variance across dimensions, ensuring effective feature transformation. Experiments on LibriSpeech and FLEURS datasets show MKL-VC significantly improves content preservation and robustness with short reference audio, outperforming kNN-VC. MKL-VC achieves performance comparable to FACodec, especially in cross-lingual voice conversion domain.
Voice conversion has emerged as a pivotal technology in numerous applications ranging from assistive communication to entertainment. In this paper, we present RT-VC, a zero-shot real-time voice conversion system that delivers ultra-low latency and high-quality performance. Our approach leverages an articulatory feature space to naturally disentangle content and speaker characteristics, facilitating more robust and interpretable voice transformations. Additionally, the integration of differentiable digital signal processing (DDSP) enables efficient vocoding directly from articulatory features, significantly reducing conversion latency. Experimental evaluations demonstrate that, while maintaining synthesis quality comparable to the current state-of-the-art (SOTA) method, RT-VC achieves a CPU latency of 61.4 ms, representing a 13.3\% reduction in latency.
Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional variational autoencoder, focusing on reducing source timbre leakage and improving linguistic-acoustic disentanglement for better style transfer. To minimize style leakage, we use multilingual discrete speech units for content representation and reinforce embeddings with augmentation-based similarity loss and mix-style layer normalization. To enhance expressivity transfer, we incorporate local F0 information via cross-attention and extract style embeddings enriched with global pitch and energy features. Experiments show our model outperforms baselines in emotion and speaker similarity, demonstrating superior style adaptation and reduced source style leakage.
Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many objective metrics like the Perceptual Evaluation of Speech Quality (PESQ), Perceptual Objective Listening Quality Assessment (POLQA) or Short-Time Objective Intelligibility (STOI) but none of them is feasible in selecting the best model. On the other hand subjective metric like Mean Opinion Score is highly reliable but it requires a lot of manual efforts and are time-consuming. To counter the issues in MOS Evaluation, we have developed a novel model, Speaker Agnostic Latent Features (SALF)-Mean Opinion Score (MOS) which is a small-sized, end-to-end, highly generalized and scalable model for predicting MOS score on a scale of 5. We use the sequences of convolutions and stack them to get the latent features of the audio samples to get the best state-of-the-art results based on mean squared error (MSE), Linear Concordance Correlation coefficient (LCC), Spearman Rank Correlation Coefficient (SRCC) and Kendall Rank Correlation Coefficient (KTAU).
Automatic speech recognition (ASR) systems struggle with dysarthric speech due to high inter-speaker variability and slow speaking rates. To address this, we explore dysarthric-to-healthy speech conversion for improved ASR performance. Our approach extends the Rhythm and Voice (RnV) conversion framework by introducing a syllable-based rhythm modeling method suited for dysarthric speech. We assess its impact on ASR by training LF-MMI models and fine-tuning Whisper on converted speech. Experiments on the Torgo corpus reveal that LF-MMI achieves significant word error rate reductions, especially for more severe cases of dysarthria, while fine-tuning Whisper on converted data has minimal effect on its performance. These results highlight the potential of unsupervised rhythm and voice conversion for dysarthric ASR. Code available at: https://github.com/idiap/RnV
As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two types of mismatches arise: one for the inputs to the content encoder during training and inference, and another for the inputs to the speaker encoder. To address these mismatches, we propose a novel VC training method called \textit{PseudoVC} in this paper. First, we introduce an innovative information perturbation approach named \textit{Pseudo Conversion} to tackle the first mismatch problem. This approach leverages pretrained VC models to convert the source utterance into a perturbed utterance, which is fed into the content encoder during training. Second, we propose an approach termed \textit{Speaker Sampling} to resolve the second mismatch problem, which will substitute the input to the speaker encoder by another utterance from the same speaker during training. Experimental results demonstrate that our proposed \textit{Pseudo Conversion} outperforms previous information perturbation methods, and the overall \textit{PseudoVC} method surpasses publicly available VC models. Audio examples are available.
Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize source speech into Hubert content tokens, eliminating much content-irrelevant information. By leveraging a Mask Generative Transformer for in-context duration modeling, our model adapts the linguistic content duration to the desired target speaking style, facilitating the transfer of the target speaker's rhythm. Furthermore, R-VC introduces a powerful Diffusion Transformer (DiT) with shortcut flow matching during training, conditioning the network not only on the current noise level but also on the desired step size, enabling high timbre similarity and quality speech generation in fewer sampling steps, even in just two, thus minimizing latency. Experimental results show that R-VC achieves comparable speaker similarity to state-of-the-art VC methods with a smaller dataset, and surpasses them in terms of speech naturalness, intelligibility and style transfer performance.
Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited effectiveness, motivating the integration of explicit text modeling. We propose StarVC, a unified autoregressive VC framework that first predicts text tokens before synthesizing acoustic features. The experiments demonstrate that StarVC outperforms conventional VC methods in preserving both linguistic content (i.e., WER and CER) and speaker characteristics (i.e., SECS and MOS). Audio demo can be found at: https://thuhcsi.github.io/StarVC/.
Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of current ADI systems is limited by poor generalization to out-of-domain speech. In this paper, we present an effective approach based on voice conversion for training ADI models that achieves state-of-the-art performance and significantly improves robustness in cross-domain scenarios. Evaluated on a newly collected real-world test set spanning four different domains, our approach yields consistent improvements of up to +34.1% in accuracy across domains. Furthermore, we present an analysis of our approach and demonstrate that voice conversion helps mitigate the speaker bias in the ADI dataset. We release our robust ADI model and cross-domain evaluation dataset to support the development of inclusive speech technologies for Arabic.
Human to non-human voice conversion (H2NH-VC) transforms human speech into animal or designed vocalizations. Unlike prior studies focused on dog-sounds and 16 or 22.05kHz audio transformation, this work addresses a broader range of non-speech sounds, including natural sounds (lion-roars, birdsongs) and designed voice (synthetic growls). To accomodate generation of diverse non-speech sounds and 44.1kHz high-quality audio transformation, we introduce a preprocessing pipeline and an improved CVAE-based H2NH-VC model, both optimized for human and non-human voices. Experimental results showed that the proposed method outperformed baselines in quality, naturalness, and similarity MOS, achieving effective voice conversion across diverse non-human timbres. Demo samples are available at https://nc-ai.github.io/speech/publications/nonhuman-vc/
Evaluating L2 speech intelligibility is crucial for effective computer-assisted language learning (CALL). Conventional ASR-based methods often focus on native-likeness, which may fail to capture the actual intelligibility perceived by human listeners. In contrast, our work introduces a novel, perception based L2 speech intelligibility indicator that leverages a native rater's shadowing data within a sequence-to-sequence (seq2seq) voice conversion framework. By integrating an alignment mechanism and acoustic feature reconstruction, our approach simulates the auditory perception of native listeners, identifying segments in L2 speech that are likely to cause comprehension difficulties. Both objective and subjective evaluations indicate that our method aligns more closely with native judgments than traditional ASR-based metrics, offering a promising new direction for CALL systems in a global, multilingual contexts.
Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speaking style of the source speaker or mimic the distinctive speaking style of the target speaker, thereby limiting the controllability of voice conversion. In this work, we propose Discl-VC, a novel voice conversion framework that disentangles content and prosody information from self-supervised speech representations and synthesizes the target speaker's voice through in-context learning with a flow matching transformer. To enable precise control over the prosody of generated speech, we introduce a mask generative transformer that predicts discrete prosody tokens in a non-autoregressive manner based on prompts. Experimental results demonstrate the superior performance of Discl-VC in zero-shot voice conversion and its remarkable accuracy in prosody control for synthesized speech.
Controllable emotional voice conversion (EVC) aims to manipulate emotional expressions to increase the diversity of synthesized speech. Existing methods typically rely on predefined labels, reference audios, or prespecified factor values, often overlooking individual differences in emotion perception and expression. In this paper, we introduce PromptEVC that utilizes natural language prompts for precise and flexible emotion control. To bridge text descriptions with emotional speech, we propose emotion descriptor and prompt mapper to generate fine-grained emotion embeddings, trained jointly with reference embeddings. To enhance naturalness, we present a prosody modeling and control pipeline that adjusts the rhythm based on linguistic content and emotional cues. Additionally, a speaker encoder is incorporated to preserve identity. Experimental results demonstrate that PromptEVC outperforms state-of-the-art controllable EVC methods in emotion conversion, intensity control, mixed emotion synthesis, and prosody manipulation. Speech samples are available at https://jeremychee4.github.io/PromptEVC/.
We introduce ArVoice, a multi-speaker Modern Standard Arabic (MSA) speech corpus with diacritized transcriptions, intended for multi-speaker speech synthesis, and can be useful for other tasks such as speech-based diacritic restoration, voice conversion, and deepfake detection. ArVoice comprises: (1) a new professionally recorded set from six voice talents with diverse demographics, (2) a modified subset of the Arabic Speech Corpus; and (3) high-quality synthetic speech from two commercial systems. The complete corpus consists of a total of 83.52 hours of speech across 11 voices; around 10 hours consist of human voices from 7 speakers. We train three open-source TTS and two voice conversion systems to illustrate the use cases of the dataset. The corpus is available for research use.
Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamental structures of phonemes and syllables are destroyed. However, they still retain tonal patterns that enable perceptual speaker identification despite losing linguistic content. In this paper, we propose leveraging speaker representations learned from time reversed speech as an augmentation strategy to enhance speaker representation. Notably, speaker and language disentanglement in voice conversion (VC) is essential to accurately preserve a speaker's unique vocal traits while minimizing interference from linguistic content. The effectiveness of the proposed approach is evaluated in the context of state-of-the-art diffusion-based VC models. Experimental results indicate that the proposed approach significantly improves speaker similarity-related scores while maintaining high speech quality.
Controlling singing style is crucial for achieving an expressive and natural singing voice. Among the various style factors, vibrato plays a key role in conveying emotions and enhancing musical depth. However, modeling vibrato remains challenging due to its dynamic nature, making it difficult to control in singing voice conversion. To address this, we propose VibESVC, a controllable singing voice conversion model that explicitly extracts and manipulates vibrato using discrete wavelet transform. Unlike previous methods that model vibrato implicitly, our approach decomposes the F0 contour into frequency components, enabling precise transfer. This allows vibrato control for enhanced flexibility. Experimental results show that VibE-SVC effectively transforms singing styles while preserving speaker similarity. Both subjective and objective evaluations confirm high-quality conversion.
Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in speech, ideal representations should disentangle content from unwanted variations like speaker characteristics in the SSL representations. However, removing speaker information often degrades other speech components, and existing methods either fail to fully disentangle speaker identity or require resource-intensive models. In this paper, we propose a novel disentanglement method that linearly decomposes SSL representations into speaker-specific and speaker-independent components, effectively generating speaker disentangled representations. Comprehensive experiments show that our approach achieves speaker independence and as such, when applied to content-driven tasks such as voice conversion, our representations yield significant improvements over state-of-the-art methods.
Speaker anonymization seeks to conceal a speaker's identity while preserving the utility of their speech. The achieved privacy is commonly evaluated with a speaker recognition model trained on anonymized speech. Although this represents a strong attack, it is unclear which aspects of speech are exploited to identify the speakers. Our research sets out to unveil these aspects. It starts with kNN-VC, a powerful voice conversion model that performs poorly as an anonymization system, presumably because of prosody leakage. To test this hypothesis, we extend kNN-VC with two interpretable components that anonymize the duration and variation of phones. These components increase privacy significantly, proving that the studied prosodic factors encode speaker identity and are exploited by the privacy attack. Additionally, we show that changes in the target selection algorithm considerably influence the outcome of the privacy attack.