阿尔茨海默症(Alzheimer's Disease,AD)是一种神经退行性疾病,患者会出现失语症、语言流畅性降低等症状.目前已经有研究者使用发音特征,流畅性、停顿等副语言学特征,或者从转录的文本中提取特征检测阿尔茨海默症.但是,传统声学特征检测方法难以获取语义信息,而将语音转录成文本又费时费力,并且由于老年人口音、患病等影响,转录质量下降明显.本文使用离散变分自编码器(discrete Variational Autoencoders,dVAE)将语音转换为伪音素序列后,利用BERT(Bidirectional Encoder Representations from Transformers)模型对伪音素序列的连接关系进行建模,提出一种dVAE-BERT模型,从而提取音频在语言维度的表征.该模型在ADReSSo(Alzheimer's Dementia Recogni-tion through Spontaneous Speech only)数据集上,模型的准确率为70.42%,比基线系统提高5.63%,其与Wav2vec2.0、Hu-BERT(Hidden-unit BERT)模型融合后,准确率分别为76.06%、71.83%.
Detection of Alzheimer's Disease Based on dVAE-BERT Model
Alzheimer's disease(AD)is a neurodegenerative disease that causes symptoms such as aphasia and de-creased speech fluency.Researchers have used articulatory features,paralinguistic features such as fluency and pauses,or features extracted from transcribed text to detect Alzheimer's disease.However,traditional acoustic feature detection meth-ods are difficult to obtain semantic information,while transcribing speech into text is time-consuming and laborious,and the quality of transcription is significantly degraded due to the effects of accent and disease in the elderly.In this paper,we propose a dVAE-BERT(discrete Variational Autoencoders-Bidirectional Encoder Representations from Transformers)mod-el,which uses discrete Variational Autoencoders(dVAE)to convert speech into pseudo-phoneme sequences,and then uses the Bidirectional Encoder Representations from Transformers(BERT)model to model the connection relations of the pseu-do-phoneme sequences to extract the representation of audio in the language dimension.The accuracy of the model on the ADReSSo(Alzheimer's Dementia Recognition through Spontaneous Speech only)dataset is 70.42%,which is 5.63%better than the baseline system,and its accuracy is 76.06%and 71.83%after fusion with Wav2vec2.0 and Hidden-unit BERT(Hu-BERT)models,respectively.
万方数据
维普
