小米(01810.HK) 正式发布并开源工业级目标说话人语音识别大模型Xiaomi-CocktailASR-1,旨在解决“鸡尾酒会”难题。该模型采用端到端LLM架构,以目标说话人的一段参考音频作为声纹提示,可在多人同时说话的复杂环境中,精准提取并仅转录目标用户的语音。在多个主流多说话人测试集上均达到SOTA,大幅领先现有方案。同时,其单人识别性能比肩标准ASR模型,可无缝兼顾单人说话场景;具备拒识...
Source Link小米(01810.HK) 正式发布并开源工业级目标说话人语音识别大模型Xiaomi-CocktailASR-1,旨在解决“鸡尾酒会”难题。该模型采用端到端LLM架构,以目标说话人的一段参考音频作为声纹提示,可在多人同时说话的复杂环境中,精准提取并仅转录目标用户的语音。在多个主流多说话人测试集上均达到SOTA,大幅领先现有方案。同时,其单人识别性能比肩标准ASR模型,可无缝兼顾单人说话场景;具备拒识...
Source LinkDisclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.