On January 20, 2025, Doubao App officially released its latest 'end-to-end' voice large model, with significant updates to its real-time voice call functionality. This development marks another leap for Doubao in the field of voice interaction, surpassing the previous ASR (Automatic Speech Recognition), LLM (Large Language Model), and TTS (Text-to-Speech) cascading solutions by integrating voice recognition, understanding, and generation into a single model. After testing by 'Intelligent Emergence,' the standout feature of the new Doubao version is its human-like capabilities.

The Seed-ASR engine launched by ByteDance achieves high-precision recognition of Mandarin, 13 Chinese dialects, and 7 foreign languages through massive training data, significantly enhancing the convenience of cross-language communication. Its key advantage lies in its excellent contextual awareness, accurately recognizing proper nouns, place names, and keywords by incorporating historical information, especially performing exceptionally well in specific scenarios, thereby improving recognition accuracy. Whether in daily conversations, complex meetings, or interactions among multiple people in noisy environments, Seed-ASR can transcribe accurately. It can also recognize various professional terms.

Recently, a new image super-resolution model called AuraSR has garnered widespread attention in the artificial intelligence community. Developed by Fal AI, this model is based on Adobe's latest GigaGAN paper and utilizes Generative Adversarial Network (GAN) technology to significantly enhance image resolution in a very short time.

AuraSR, a colossal upsampling model with 600 million parameters, is derived from the GigaGAN paper and is now fully open-sourced. The strength of this model lies in its ability to enlarge images by four times while supplementing details that may be lost during the magnification process. Moreover, this is not all it can do; it can even perform multiple magnifications on images, enriching the details further.

Tencent Cloud ASR has been upgraded to better handle dialects and noise. ASR supports recognition of 23 dialects and noise filtering. The large language model enhances recognition accuracy. The product is widely used by both internal and external enterprise clients, with Tencent Cloud ASR reaching a daily call volume of over 10 billion.

Amazon has released a next-generation ASR system that covers over 100 languages, providing comprehensive automatic speech recognition services. The speech foundation model improves accuracy by 20% to 50%, with enhancements of 30% to 70% in challenging areas such as telephone speech. The system supports multiple features, including automatic punctuation, custom vocabulary, automatic language identification, and speaker separation. Thousands of businesses are leveraging Amazon Transcribe to unlock insights from audio content, enhancing accessibility and discoverability.

OpenAI announced the upgraded automatic speech recognition model Whisper3 at the Developer Day. Whisper3 offers multi-language support and can quickly and accurately transcribe audio to text. OpenAI plans to make the Whisper3 API available to users.