Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing systems struggle to maintain speaker consistency, model overlapping speech, and synthesize coherent conversations efficiently. In this paper, we introduce CoVoMix2, a fully non-autoregressive framework for zero-shot multi-talker dialogue generation. CoVoMix2 directly predicts mel-spectrograms from multi-stream transcriptions using a flow-matching-based generative model, eliminating the reliance on intermediate token representations. To better capture realistic conversational dynamics, we propose transcription-level speaker disentanglement, sentence-level alignment, and prompt-level random masking strategies. Our approach achieves state-of-the-art performance, outperforming strong baselines like MoonCast and Sesame in speech quality, speaker consistency, and inference speed. Notably, CoVoMix2 operates without requiring transcriptions for the prompt and supports controllable dialogue generation, including overlapping speech and precise timing control, demonstrating strong generalizability to real-world speech generation scenarios.

Cross-speaker emotion transfer in speech synthesis relies on extracting speaker-independent emotion embeddings for accurate emotion modeling without retaining speaker traits. However, existing timbre compression methods fail to fully separate speaker and emotion characteristics, causing speaker leakage and degraded synthesis quality. To address this, we propose DiEmo-TTS, a self-supervised distillation method to minimize emotional information loss and preserve speaker identity. We introduce cluster-driven sampling and information perturbation to preserve emotion while removing irrelevant factors. To facilitate this process, we propose an emotion clustering and matching approach using emotional attribute prediction and speaker embeddings, enabling generalization to unlabeled data. Additionally, we designed a dual conditioning transformer to integrate style features better. Experimental results confirm the effectiveness of our method in learning speaker-irrelevant emotion embeddings.

While signal conversion and disentangled representation learning have shown promise for manipulating data attributes across domains such as audio, image, and multimodal generation, existing approaches, especially for speech style conversion, are largely empirical and lack rigorous theoretical foundations to guarantee reliable and interpretable control. In this work, we propose a general framework for speech attribute conversion, accompanied by theoretical analysis and guarantees under reasonable assumptions. Our framework builds on a non-probabilistic autoencoder architecture with an independence constraint between the predicted latent variable and the target controllable variable. This design ensures a consistent signal transformation, conditioned on an observed style variable, while preserving the original content and modifying the desired attribute. We further demonstrate the versatility of our method by evaluating it on speech styles, including speaker identity and emotion. Quantitative evaluations confirm the effectiveness and generality of the proposed approach.

We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW) encoder to extract target-speaker embeddings, which are concatenated into a single representation and passed to a shared decoder. This enables the model to transcribe overlapping speech as a serialized output stream with speaker tags and timestamps. In contrast to target-speaker ASR systems such as DiCoW, which decode each speaker separately, our approach performs joint decoding, allowing the decoder to condition on the context of all speakers simultaneously. Experiments show that the model outperforms existing SOT-based approaches and surpasses DiCoW on multi-talker mixtures (e.g., LibriMix).

In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner.

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.

Speech disorders can make communication hard or even impossible for those who develop them. Personalised Text-to-Speech is an attractive option as a communication aid. We attempt voice reconstruction using a large speech model, with which we generate an approximation of a dysarthric speaker's voice prior to the onset of their condition. In particular, we investigate whether a state-of-the-art large speech model, Parler TTS, can generate intelligible speech while maintaining speaker identity. We curate a dataset and annotate it with relevant speaker and intelligibility information, and use this to fine-tune the model. Our results show that the model can indeed learn to generate from the distribution of this challenging data, but struggles to control intelligibility and to maintain consistent speaker identity. We propose future directions to improve controllability of this class of model, for the voice reconstruction task.

ABSTRACT We present ChiReSSD, a speech reconstruction framework that preserves children speaker's identity while suppressing mispronunciations. Unlike prior approaches trained on healthy adult speech, ChiReSSD adapts to the voices of children with speech sound disorders (SSD), with particular emphasis on pitch and prosody. We evaluate our method on the ST AR dataset and report substantial improvements in lexical accuracy and speaker identity preservation. Furthermore, we automatically predict the phonetic content in the original and reconstructed pairs, where the proportion of corrected consonants is comparable to the percentage of correct consonants (PCC), a clinical speech assessment metric. Our experiments show Pearson correlation of ρ = 0.63 between automatic and human expert annotations, highlighting the potential to reduce the manual transcription burden. In addition, experiments on the TORGO dataset demonstrate effective generalization for reconstructing adult dysarthric speech. Our results indicate that disentangled, style-based TTS reconstruction can provide identity-preserving speech across diverse clinical populations.

Abstract--Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system outputs. While targeted attacks on end-to-end ASR models have been widely studied, the phonetic basis of these perturbations and their effect on speaker identity remain underexplored. In this work, we analyze adversarial audio at the phonetic level and show that perturbations are associated with systematic phonetic tendencies, such as vowel centralization and consonant substitutions. Using the DeepSpeech ASR model as our target, we generate targeted adversarial examples and evaluate their impact on speaker identity embeddings across genuine and impostor samples. Results across 16 phonetically diverse target phrases demonstrate that adversarial audio induces both transcription errors and identity drift, highlighting the need for phonetic-aware defenses to ensure the robustness of ASR and speaker recognition systems.

We propose Llama-Mimi, a speech language model that uses a unified tokenizer and a single Transformer decoder to jointly model sequences of interleaved semantic and acoustic tokens. Comprehensive evaluation shows that Llama-Mimi achieves state-of-the-art performance in acoustic consistency and possesses the ability to preserve speaker identity. Our analysis further demonstrates that increasing the number of quantizers improves acoustic fidelity but degrades linguistic performance, highlighting the inherent challenge of maintaining long-term coherence. We additionally introduce an LLM-as-a-Judge-based evaluation to assess the spoken content quality of generated outputs. Our models, code, and speech samples are publicly available.