arXiv:2609.38157v1 Announce Type: cross Abstract: Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional train...
arXiv:2602. 03420v2 Announce Type: replace-cross Abstract: Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content.
arXiv:2608.30325v1 Announce Type: new Abstract: Natural-language instructions enable flexible control of synthesized speech, yet emotional TTS systems primarily model a single utterance-level affect,...
The paper investigates emotion steering in Moshi, a fully open‑source full‑duplex speech language model, across four emotions. Using mean‑difference activation steering—just a few vector additions per frame and no retraining—the authors find that emotion can be linearly decoded from Moshi’s residual stream, but steering is only partially achievable and uneven: happy, angry and surprise steer toward a shared direction while sad is distinctly steerable. They also demonstrate that the shared component across the three emotions cannot simply be projected away from all emotions equally.
arXiv:2607. 00946v1 Announce Type: cross Abstract: While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for steerability, remain poorly understood.
EmoTra‑TTS introduces a method for smooth intra‑utterance emotion transitions in speech synthesis. It uses a multi‑pass flow blending pipeline, dual‑stage VAD conditioning, and direction‑magnitude decoupled injection to generate frame‑aligned emotional prosody. The system adds only 0.43% more parameters, incurs no latency, and outperforms four state‑of‑the‑art baselines and two commercial systems in emotion transition quality and overall preference tests.
arXiv:2606. 14922v1 Announce Type: cross Abstract: For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning.
The paper introduces a discriminative adaptation for SpeechLLMs that reads the hidden state of the final prompt token via a simple classification head, enabling emotion recognition in a single forward pass without altering the backbone. This approach replaces the generative decoder, which can produce out‑of‑set labels and favor frequent classes, with a controlled comparison between generative and discriminative inference. Experiments on IEMOCAP show improved Macro F1 scores, elimination of hallucinations, and larger gains on realistic ASR transcripts, while revealing that emotion directions encode indirect associations reflecting web‑scale text biases.
arXiv:2607. 15755v1 Announce Type: cross Abstract: Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions.
arXiv:2606. 07293v1 Announce Type: cross Abstract: Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity.
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated...
arXiv:2610.07647v1 Announce Type: cross Abstract: Speech becomes less intelligible in noisy environments, and humans naturally adapt their voice to compensate. Inspired by this behavior, we investiga...