Child Speech Disorder Detection with Siamese Recurrent Network Using Speech Attribute Features

Abstract

Acoustics-based automatic assessment is a highly desirable approach to detecting speech sound disorder (SSD) in children. The performance of an automatic speech assessment system depends greatly on the availability of a good amount of properly annotated disordered speech, which is a critical problem particularly for child speech. This paper presents a novel design of child speech disorder detection system that requires only normal speech for model training. The system is based on a Siamese recurrent network, which is trained to learn the similarity and discrepancy of pronunciations between a pair of phones in the embedding space. For detection of speech sound disorder, the trained network measures a distance that contrasts the test phone to the desired phone and the distance is used to train a binary classifier. Speech attribute features are incorporated to measure the pronunciation quality and provide diagnostic feedback. Experimental results show that Siamese recurrent network with a combination of speech attribute features and phone posterior features could attain an optimal detection accuracy of 0.941.

Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling

“…Mauro et al incorporate the speech of a reference speaker to detect mispronunciations at the phoneme level [11]. Wang et al use siamese networks for modeling discrepancy between normal and distorted children's speech [12]. We take a similar approach but we do not need a database of reference speech.…”

Al-Quran recitation verification for memorization test using Siamese LSTM network

“…The absolute difference of the two LSTM networks' output is calculated and then fed as input to the fully connected layer with the two outputs as illustrated in figure 3. This architecture is similar with the one used in [19]. Henceforth, the first model will be referred to as MaLSTM, while the second model is called Siamese-Classifier.…”

Classifying Speech Intelligibility Levels of Children in Two Continuous Speech Styles

“…GRU is a simplified architecture with an efficiency degree that is comparable to LSTM. These two approaches have been adopted for building automatic speech assessment systems [10,[16][17][18][19], e.g., the work done by Korzekwa et al on dysarthric speech [16].…”

“…Mel-frequency cepstral coefficients (MFCCs) are commonly used in speech assessment systems for acoustic modeling [10,[17][18][19]24] and feature extraction [25,26]. While deep learning models recently attract intense attentions, Mel Spectrogram is also getting increasingly popular [10,12,16].…”

“…Mixed features did not improve the performance significantly. In addition to model enhancement, we will also experiment on integrating information about onset consonants and feature attributes that have been proved useful for assessing pathological speech into our AP features [19].…”