Related papers: Accelerating Flow-Matching-Based Text-to-Speech vi…

Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end model, yielding promising results. However, the training of…

Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token per forward pass, which limits throughput and inflates latency for long sequences. Diffusion Language Models (DLMs)…

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during…

Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive…

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a…

We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-grained prosody transfer between any pair of seen speakers.…

While prompt-based text-to-speech (TTS) models enable natural language-driven speaking style control, they often provide limited fine-grained control and apply a single global style across an utterance. This restricts practical use cases…

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental…

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose SpotlightTTS,…

People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich…

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce UmbraTTS, a flow-matching based TTS model that jointly…

Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time…

We present VoXtream, a fully autoregressive, zero-shot streaming text-to-speech (TTS) system for real-time use that begins speaking from the first word. VoXtream directly maps incoming phonemes to audio tokens using a monotonic alignment…

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…