CALM：多说话人ASR的联合上下文语音-语言建模
CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
AI总结：
CALM通过端到端框架整合目标说话人条件和上下文偏差，降低多说话人语音识别的词错误率和字符错误率，验证了跨语言的联合语音-语言建模有效性。
摘要：
我们提出了CALM，一种用于多说话人自动语音识别（ASR）的联合上下文语音-语言建模框架。在个性化AI场景中，语音和语言线索的联合可用性自然推动了目标说话人条件与重叠对话上下文偏差的整合。CALM通过说话人嵌入驱动的目标说话人提取和动态词汇基于的上下文偏差实现这一整合。我们评估了CALM在模拟英语（LibriSpeechMix）和日语（自发日语混合语料库，CSJMix）。在双说话人混合中，CALM在LibriSpeech2Mix上将有偏词错误率（B-WER）从12.7降至4.7，在CSJMix2（eval3）上将有偏字符错误率（B-CER）从16.6降至8.4，验证了跨语言的联合语音-语言建模有效性。我们还报告了AMI语料库（IHM-mix条件）上的结果，以验证在标准化语音混合中的性能。
英文摘要：
We present CALM, a joint Contextual Acoustic-Linguistic Modeling framework for multi-speaker automatic speech recognition (ASR). In personalized AI scenarios, the joint availability of acoustic and linguistic cues naturally motivates the integration of target-speaker conditioning with contextual biasing in overlapping conversations. CALM implements this integration in an end-to-end framework through speaker embedding-driven target-speaker extraction and dynamic vocabulary-based contextual biasing. We evaluate CALM on simulated English (LibriSpeechMix) and Japanese (Corpus of Spontaneous Japanese mixtures, CSJMix). On two-speaker mixtures, CALM reduces biased word error rate (B-WER) from 12.7 to 4.7 on LibriSpeech2Mix and biased character error rate (B-CER) from 16.6 to 8.4 on CSJMix2 (eval3), demonstrating the effectiveness of joint acoustic-linguistic modeling across languages. We additionally report results on the AMI corpus (IHM-mix condition) to validate performance on standardized speech mixtures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
