Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker identity. Because SC is constrained to a single audio stream, it offers a more direct setting for probing biases in speech foundation models than dialogue does. In this work we present the first systematic evaluation of bias in SC, investigating how gender and phonation type (breathy, creaky, end-creak) affect continuation behaviour. We evaluate three recent models: SpiritLM (base and expressive), VAE-GSLM, and SpeechGPT across speaker similarity, voice quality preservation, and text-based bias metrics. Results show that while both speaker similarity and coherence remain a challenge, textual evaluations reveal significant model and gender interactions: once coherence is sufficiently high (for VAE-GSLM), gender effects emerge on text-metrics such as agency and sentence polarity. In addition, continuations revert toward modal phonation more strongly for female prompts than for male ones, revealing a systematic voice-quality bias. These findings highlight SC as a controlled probe of socially relevant representational biases in speech foundation models, and suggest that it will become an increasingly informative diagnostic as continuation quality improves.

Perceptual voice quality dimensions describe key characteristics of atypical speech and other speech modulations. Here we develop and evaluate voice quality models for seven voice and speech dimensions (intelligibility, imprecise consonants, harsh voice, naturalness, monoloudness, monopitch, and breathiness). Probes were trained on the public Speech Accessibility (SAP) project dataset with 11,184 samples from 434 speakers, using embeddings from frozen pre-trained models as features. We found that our probes had both strong performance and strong generalization across speech elicitation categories in the SAP dataset. We further validated zero-shot performance on additional datasets, encompassing unseen languages and tasks: Italian atypical speech, English atypical speech, and affective speech. The strong zero-shot performance and the interpretability of results across an array of evaluations suggests the utility of using voice quality dimensions in speaking style-related tasks.

Current accent conversion (AC) systems do not disentangle the two main sources of non-native accent: segmental and prosodic characteristics. Being able to manipulate a non-native speaker's segmental and/or prosodic channels independently is critical to quantify how these two channels contribute to speech comprehensibility and social attitudes. We present an AC system that not only decouples voice quality from accent, but also disentangles the latter into its segmental and prosodic characteristics. The system is able to generate accent conversions that combine (1) the segmental characteristics from a source utterance, (2) the voice characteristics from a target utterance, and (3) the prosody of a reference utterance. We show that vector quantization of acoustic embeddings and removal of consecutive duplicated codewords allows the system to transfer prosody and improve voice similarity. We conduct perceptual listening tests to quantify the individual contributions of segmental features and prosody on the perceived comprehensibility of non-native speech. Our results indicate that, contrary to prior research in non-native speech, segmental features have a larger impact on comprehensibility than prosody. The proposed AC system may also be used to study how segmental and prosody cues affect social attitudes towards non-native speech.

Perceptual modification of voice is an elusive goal. While non-experts can modify an image or sentence perceptually with available tools, it is not clear how to similarly modify speech along perceptual axes. Voice conversion does make it possible to convert one voice to another, but these modifications are handled by black box models, and the specifics of what perceptual qualities to modify and how to modify them are unclear. Towards allowing greater perceptual control over voice, we introduce PerMod, a conditional latent diffusion model that takes in an input voice and a perceptual qualities vector, and produces a voice with the matching perceptual qualities. Unlike prior work, PerMod generates a new voice corresponding to specific perceptual modifications. Evaluating perceptual quality vectors with RMSE from both human and predicted labels, we demonstrate that PerMod produces voices with the desired perceptual qualities for typical voices, but performs poorly on atypical voices.

The Consensus Auditory-Perceptual Evaluation of Voice is a widely employed tool in clinical voice quality assessment that is significant for streaming communication among clinical professionals and benchmarking for the determination of further treatment. Currently, because the assessment relies on experienced clinicians, it tends to be inconsistent, and thus, difficult to standardize. To address this problem, we propose to leverage lightly weighted automatic audio parameter extraction, to increase the clinical relevance, reduce the complexity, and enhance the interpretability of voice quality assessment. The proposed method utilizes age, sex, and five audio parameters: jitter, absolute jitter, shimmer, harmonic-to-noise ratio (HNR), and zero crossing. A classical machine learning approach is employed. The result reveals that our approach performs similar to state-of-the-art (SOTA) methods, and outperforms the latent representation obtained by using popular audio pre-trained models. This approach provide insights into the feasibility of different feature extraction approaches for voice evaluation. Audio parameters such as jitter and the HNR are proven to be suitable for characterizing voice quality attributes, such as roughness and strain. Conversely, pre-trained models exhibit limitations in effectively addressing noise-related scorings. This study contributes toward more comprehensive and precise voice quality evaluations, achieved by a comprehensively exploring diverse assessment methodologies.

Prior studies in the automatic classification of voice quality have mainly studied the use of the acoustic speech signal as input. Recently, a few studies have been carried out by jointly using both speech and neck surface accelerometer (NSA) signals as inputs, and by extracting MFCCs and glottal source features. This study examines simultaneously-recorded speech and NSA signals in the classification of voice quality (breathy, modal, and pressed) using features derived from three self-supervised pre-trained models (wav2vec2-BASE, wav2vec2-LARGE, and HuBERT) and using a SVM as well as CNNs as classifiers. Furthermore, the effectiveness of the pre-trained models is compared in feature extraction between glottal source waveforms and raw signal waveforms for both speech and NSA inputs. Using two signal processing methods (quasi-closed phase (QCP) glottal inverse filtering and zero frequency filtering (ZFF)), glottal source waveforms are estimated from both speech and NSA signals. The study has three main goals: (1) to study whether features derived from pre-trained models improve classification accuracy compared to conventional features (spectrogram, mel-spectrogram, MFCCs, i-vector, and x-vector), (2) to investigate which of the two modalities (speech vs. NSA) is more effective in the classification task with pre-trained model-based features, and (3) to evaluate whether the deep learning-based CNN classifier can enhance the classification accuracy in comparison to the SVM classifier. The results revealed that the use of the NSA input showed better classification performance compared to the speech signal. Between the features, the pre-trained model-based features showed better classification accuracies, both for speech and NSA inputs compared to the conventional features. It was also found that the HuBERT features performed better than the wav2vec2-BASE and wav2vec2-LARGE features.

Text to Speech (TTS) models can generate natural and high-quality speech, but it is not expressive enough when synthesizing speech with dramatic expressiveness, such as stand-up comedies. Considering comedians have diverse personal speech styles, including personal prosody, rhythm, and fillers, it requires real-world datasets and strong speech style modeling capabilities, which brings challenges. In this paper, we construct a new dataset and develop ComedicSpeech, a TTS system tailored for the stand-up comedy synthesis in low-resource scenarios. First, we extract prosody representation by the prosody encoder and condition it to the TTS model in a flexible way. Second, we enhance the personal rhythm modeling by a conditional duration predictor. Third, we model the personal fillers by introducing comedian-related special tokens. Experiments show that ComedicSpeech achieves better expressiveness than baselines with only ten-minute training data for each comedian. The audio samples are available at https://xh621.github.io/stand-up-comedy-demo/

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source-filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch controllability. However, the high temporal resolution inputs result in high computation costs. Although the HiFi-GAN vocoder achieves fast high-fidelity voice generation thanks to the efficient upsampling-based generator architecture, the pitch controllability is severely limited. To realize a fast and pitch-controllable high-fidelity neural vocoder, we introduce the source-filter theory into HiFi-GAN by hierarchically conditioning the resonance filtering network on a well-estimated source excitation information. According to the experimental results, our proposed method outperforms HiFi-GAN and uSFGAN on a singing voice generation in voice quality and synthesis speed on a single CPU. Furthermore, unlike the uSFGAN vocoder, the proposed method can be easily adopted/integrated in real-time applications and end-to-end systems.

This paper analyzes dysarthric speech datasets from three languages with different prosodic systems: English, Korean, and Tamil. We inspect 39 acoustic measurements which reflect three speech dimensions including voice quality, pronunciation, and prosody. As multilingual analysis, examination on the mean values of acoustic measurements by intelligibility levels is conducted. Further, automatic intelligibility classification is performed to scrutinize the optimal feature set by languages. Analyses suggest pronunciation features, such as Percentage of Correct Consonants, Percentage of Correct Vowels, and Percentage of Correct Phonemes to be language-independent measurements. Voice quality and prosody features, however, generally present different aspects by languages. Experimental results additionally show that different speech dimension play a greater role for different languages: prosody for English, pronunciation for Korean, both prosody and pronunciation for Tamil. This paper contributes to speech pathology in that it differentiates between language-independent and language-dependent measurements in intelligibility classification for English, Korean, and Tamil dysarthric speech.