Related papers: STCTS: Generative Semantic Compression for Ultra-L…

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually…

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by this success, researchers have explored adapting these methods to speech by discretizing continuous…

Speech codecs serve as a crucial bridge in unifying speech and text language models. Existing codec methods face several challenges in semantic encoding, such as residual paralinguistic information (e.g., timbre, emotion), insufficient…

The Lombard effect plays a key role in natural communication, particularly in noisy environments or when addressing hearing-impaired listeners. We present a controllable text-to-speech (TTS) system capable of synthesizing Lombard speech for…

Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, existing CSS systems are…

In this paper, we present CopyCat2 (CC2), a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually appropriate prosody, and c) transferring prosody at…

Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel accuracy and human perception. We propose a semantic video…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often…

Semantic communications have shown great potential to boost the end-to-end transmission performance. To further improve the system efficiency, in this paper, we propose a class of novel semantic coded transmission (SCT) schemes over…

In this paper, we introduce a large model-empowered streaming semantic communication system for speech transmission across various languages, named LSSC-ST. Specifically, we devise an edge-device collaborative semantic communication…

With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

State-of-the-art sequence-to-sequence acoustic networks, that convert a phonetic sequence to a sequence of spectral features with no explicit prosody prediction, generate speech with close to natural quality, when cascaded with neural…

Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from…

We present STFTCodec, a novel spectral-based neural audio codec that efficiently compresses audio using Short-Time Fourier Transform (STFT). Unlike waveform-based approaches that require large model capacity and substantial memory…

Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy…

Intonations play an important role in delivering the intention of a speaker. However, current end-to-end TTS systems often fail to model proper intonations. To alleviate this problem, we propose a novel, intuitive method to synthesize…