2018/11/07 by Hyungjun Lim, Lim, Hyungjun, Younggwan Kim +7 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Signal Processing (eess.SP) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1811.02736
openalex publication_date 2018/11/07 · openalex created_date 2018/11/16 · openalex updated_date 2026/07/28
Previous researches on acoustic word embeddings used in query-by-example spoken term detection have shown remarkable performance improvements when using a triplet network. However, the triplet network is trained using only a limited information about acoustic similarity between words. In this paper, we propose a novel architecture, phonetically associated triplet network (PATN), which aims at increasing discriminative power of acoustic word embeddings by utilizing phonetic information as well as word identity. The proposed model is learned to minimize a combined loss function that was made by introducing a cross entropy loss to the lower layer of LSTM-based triplet network. We observed that the proposed method performs significantly better than the baseline triplet network on a word discrimination task with the WSJ dataset resulting in over 20% relative improvement in recall rate at 1.0 false alarm per hour. Finally, we examined the generalization ability by conducting the out-of-domain test on the RM dataset.