基于N-Skipgram和位置一元语法匹配的无监督语音识别
Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching
AI总结：
针对无监督语音识别训练中GAN不稳定、音文不对齐及内存需求大的问题，提出结合低阶N-skipgram与位置一元语法统计的ESPUM系统，在TIMIT基准上取得有竞争力的ASR和音素分割性能，且代码已开源。
摘要：
训练无监督语音识别系统面临与GAN相关的不稳定性、语音与文本不对齐以及内存需求大的挑战。为解决这些问题，我们提出了一种新型ASR系统ESPUM。该系统利用低阶N-skipgram（最高N=3）的能力，结合从少量样本批次中收集的位置一元语法统计信息。在TIMIT基准上评估，我们的模型在ASR和音素分割任务中展现出具有竞争力的性能。可通过https://github.com/lwang114/GraphUnsupASR获取我们公开的代码。
英文摘要：
Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.
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。
