Recently, the third quarter results of speechio tiobe evaluation (hereinafter referred to as "evaluation") were announced, and Himalayan automatic speech recognition technology (hereinafter referred to as "ASR") won the first place in this evaluation. Himalaya's technology has been widely used in the "Ai manuscript function" of Himalaya app, bringing readers an integrated content consumption experience of listening, watching and listening. Speechio tiobe evaluation is an authoritative industry open evaluation project in China. It aims to objectively evaluate and record the recognition accuracy of various public speech recognition services in different fields, with word accuracy as the test index. The evaluation is conducted quarterly. Himalayan ASR technology stood out in the evaluation in the third quarter of this year, winning the championship with an ultra-low error rate of 2.16%. Other companies participating in this evaluation include Yitu, Tencent, BiliBili, Ali, Microsoft, iFLYTEK, Baidu, etc. Himalayan ASR technology is an important voice technology developed by Himalayan intelligent voice laboratory. This technology can transcribe the voice content without script in Himalayan platform and output the corresponding text, so that listeners can better understand the voice content. With the improvement of the usage rate of voice recognition functions, the ultimate optimization of details has become the key to the success of technical products. During the research and development, Himalaya developed a self-developed "end-to-end" speech recognition framework based on wenet, and deeply optimized the whole link of data reading, model structure, training method, hot word enhancement, deployment process, etc., constantly trying new paper solutions, integrating them into the self-developed framework, thus effectively reducing the error rate and reaching the industry-leading level. Himalaya ASR technology has now been widely applied to the AI document function of Himalaya app, which can effectively identify the non document sound content and generate documents for the non document sound content. At the same time, for the audio content that already has the original manuscript, the Himalayan AI manuscript function applies the alignment technology of ultra long audio and text, time stamps the sound and the manuscript, and synchronously highlights the corresponding text while playing the sound, so that users can more conveniently enjoy the content consumption experience of listening and watching. In the near future, Himalaya will launch a new version of AI manuscript function to comprehensively improve the user experience. Please look forward to it. Himalaya has been studying the field of AI voice technology for many years, and has set up the Himalaya intelligent voice laboratory, the core department, to focus on the research and development of speech synthesis, speech recognition, speech signal processing, codec and intelligent sound effects for a long time. In addition to ASR technology, Himalaya's TTS (speech synthesis) technology is also in the forefront of the industry, and has been widely used in the production of storytelling, news, novels and other contents, which is helping Himalaya to further expand the possibilities of aigc in addition to the existing "UGC + PGC + pugc" content ecology. At the same time, this year's self-developed cross language speech synthesis innovation technology paper by Himalaya and the related paper on speaker log technology in cooperation with the University of science and technology of China have been awarded the international audio top conference ICA twice