This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with different types and severities of speech impairment with training sets ranging in size from <1 minute to 18-20 minutes of speech data. Word error rate (WER) thresholds were selected to determine Success Percentage (the percentage of personalized models reaching the target WER) in different application scenarios. For the home automation scenario, 79% of speakers reached the target WER with 18-20 minutes of speech; but even with only 3-4 minutes of speech, 63% of speakers reached the target WER. Further evaluation found similar improvement on test sets with conversational and out-of-domain, unprompted phrases. Our results demonstrate that with only a few minutes of recordings, individuals with disordered speech could benefit from personalized ASR.
翻译:这项研究调查了个人化自动语音识别(ASR)的性能,以便使用少量的每个发言者的适应性数据识别有障碍的言语。我们为195名有不同类型和不同语言障碍的人培训了个性化模式,其培训范围为发言数据小于1分钟至18-20分钟不等。为确定不同应用情景的成功率(个人化模式达到目标WER的百分比),选择了单词错误率阈值。在家庭自动化情景中,79%的发言者用18-20分钟的演讲时间达到了WER目标;但即使只有3-4分钟的演讲时间,63%的发言者也达到了WER目标。进一步的评估发现,在测试器上也有类似的改进,有话语系和语系外语系,语句不受鼓励。我们的结果显示,只有几分钟的录音记录,有障碍的言论的人可以受益于个性化的ASR。