This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice.

Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal Forced Aligner, which can be time-consuming and lack flexibility. The importance of accurate duration is often underestimated, despite their crucial role in achieving natural prosody and intelligibility. To address these limitations, we propose a novel Aligner-Guided Training Paradigm that prioritizes accurate duration labelling by training an aligner before the TTS model. This approach reduces dependence on external tools and enhances alignment accuracy. We further explore the impact of different acoustic features, including Mel-Spectrograms, MFCCs, and latent features, on TTS model performance. Our experimental results show that aligner-guided duration labelling can achieve up to a 16\% improvement in word error rate and significantly enhance phoneme and tone alignment. These findings highlight the effectiveness of our approach in optimizing TTS systems for more natural and intelligible speech generation.

In a demo the company gave me last week, Joanne Jang, a product manager, showed off ChatGPT's range of synthetic voices. These were created by training the text-to-speech model on the voices of actors that OpenAI had hired. In the future it might even allow users to create their own voices. "In fashioning the voices, the number-one criterion was whether this is a voice you could listen to all day," she says. They are chatty and enthusiastic but won't be to everyone's taste.

Joe Rogan did a unique and impressive interview with Steve Jobs on podcast.ai, The founder of Apple passed away in 2011, but that didn't stop Joe Rogan from bringing his voice back to life using Artificial Intelligence. "On this episode, I welcome a friend who is difficult to describe. I am fascinated by him, and I hope you will be too. He is weird and brilliant and something insufferable. But my guest today has made some of the best technological products of our age, and he is always pushing the envelope in innovation," Joe Rogan said in his introduction during the podcast.

Researchers at Microsoft have made software that can learn the sound of your voice, and then use it to speak a language that you don't. The system could be used to make language tutoring software more personal, or to make tools for travelers. In a demonstration at Microsoft's Redmond, Washington, campus on Tuesday, Microsoft research scientist Frank Soong showed how his software could read out text in Spanish using the voice of his boss, Rick Rashid, who leads Microsoft's research efforts. In a second demonstration, Soong used his software to grant Craig Mundie, Microsoft's chief research and strategy officer, the ability to speak Mandarin. Hear Rick Rashid's voice in his native language and then translated into several other languages: English: Listen to a clip of Rick Rashid talking normally.