Learning Acoustic Word Embeddings With Phonetically Associated Triplet Network

Abstract

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-domai

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylim2018learning

Related papers

• Discriminative Acoustic Word Embeddings: Recurrent Neural Network-based Approaches (2016)0.00
• Learning Efficient Representations For Keyword Spotting With Triplet Loss (2021)11.76
• Deep Triphone Embedding Improves Phoneme Recognition (2017)0.00
• Scenario Aware Speech Recognition: Advancements For Apollo Fearless Steps & Chime-4 Corpora (2021)5.84
• Query-by-example Search With Discriminative Neural Acoustic Word Embeddings (2017)12.40
• Triplet Entropy Loss: Improving The Generalisation Of Short Speech Language Identification Systems (2020)0.00
• Additional Shared Decoder On Siamese Multi-view Encoders For Learning Acoustic Word Embeddings (2019)6.34
• Learning Acoustic Word Embeddings With Temporal Context For Query-by-example Speech Search (2018)9.92