10 articles tagged with #tts. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Voxtral TTS is a new multilingual text-to-speech AI model that can generate natural speech from just 3 seconds of reference audio. In human evaluations, it achieved a 68.4% win rate over ElevenLabs Flash v2.5 for voice cloning, demonstrating superior naturalness and expressivity.
Google AI has released WAXAL, an open multilingual speech dataset covering 24 African languages to improve Automatic Speech Recognition and Text-to-Speech systems. This addresses the significant data distribution problem where African languages remain poorly represented in speech technology training corpora.
Researchers introduce SyncSpeech, a new text-to-speech model that combines autoregressive and non-autoregressive approaches using a Temporal Mask Transformer architecture. The model achieves 5.8x lower first-packet latency and 8.8x improved real-time performance while maintaining comparable speech quality to existing models.
Researchers have developed PV-VASM, a probabilistic framework for verifying the robustness of voice anti-spoofing models against deepfake attacks. The model-agnostic approach estimates misclassification probability under various speech synthesis techniques including text-to-speech and voice cloning, providing formal robustness guarantees against unseen generation methods.
Research demonstrates that LoRA fine-tuning of large language models significantly improves text-to-speech systems, achieving up to 0.42 DNS-MOS gains and 34% SNR improvements when training data has sufficient acoustic diversity. The study establishes LoRA as an effective mechanism for speaker adaptation in compact LLM-based TTS systems, outperforming frozen base models across perceptual quality, speaker fidelity, and signal quality metrics.
Fish Audio has released S2-Pro, a flagship Large Audio Model (LAM) that enables high-fidelity, multi-speaker text-to-speech synthesis with sub-150ms latency. The system features zero-shot voice cloning capabilities and granular emotion control, representing a shift from traditional modular TTS pipelines to integrated audio models.
DuplexCascade introduces a VAD-free cascaded streaming pipeline that enables full-duplex speech-to-speech dialogue while maintaining LLM intelligence. The system converts traditional long utterance turns into micro-turn interactions using special control tokens to coordinate turn-taking and response timing.
Facebook Research introduces the Latent Speech-Text Transformer (LST), which aggregates speech tokens into higher-level patches to improve computational efficiency and cross-modal alignment. The model achieves up to +6.5% absolute gain on speech HellaSwag benchmarks while maintaining text performance and reducing inference costs for ASR and TTS tasks.
Researchers introduce NV-Bench, the first standardized benchmark for evaluating nonverbal vocalizations in text-to-speech systems. The benchmark includes 1,651 multilingual utterances across 14 categories and proposes new evaluation metrics that show strong correlation with human perception.
TTS Arena introduces a new benchmarking platform for evaluating text-to-speech models through community-driven comparisons in real-world scenarios. The platform aims to provide standardized evaluation metrics for TTS quality assessment across different models and use cases.
