Semantic Query-by-example Speech Search Using Visual Grounding

Abstract

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We follow a segmental QbE approach where variable-duration speech segments (queries, search utterances) are mapped to fixed-dimensional embedding vectors. We show that a QbE system using an embedding function trained on visually grounded speech data outperforms a purely acoustic QbE system in terms of both exact and semantic retrieval performance.

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keykamper2019semantic

Related papers

• Query-by-example Search With Discriminative Neural Acoustic Word Embeddings (2017)12.40
• Learning Acoustic Word Embeddings With Temporal Context For Query-by-example Speech Search (2018)9.92
• Semantic Speech Retrieval With A Visually Grounded Model Of Untranscribed Speech (2017)10.61
• Query-by-example Spoken Term Detection Using Attention-based Multi-hop Networks (2017)9.23
• Query-by-example Keyword Spotting Using Spectral-temporal Graph Attentive Pooling And Multi-task Learning (2024)0.00
• On The Contributions Of Visual And Textual Supervision In Low-resource Semantic Speech Retrieval (2019)6.34
• Cross-lingual Query-by-example Spoken Term Detection: A Transformer-based Approach (2024)0.00
• Neural Network Based End-to-end Query By Example Spoken Term Detection (2019)0.00