BEST-STD2.0: Balanced And Efficient Speech Tokenizer For Spoken Term Detection

Abstract

Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD systems, which use discrete speech representations, enable efficient search but struggle with robustness to noise and reverberation, and with inefficient token utilization. We address these challenges by proposing a noise and reverberation-augmented training strategy to improve tokenizer robustness. In addition, we introduce optimal transport-based regularization to ensure balanced token usage and enhance token efficiency. To further speed up retrieval, we adopt a TF-IDF-based search mechanism. Empirical evaluations demonstrate that the proposed method outperforms STD baselines across various distortion levels while maintaining high search efficiency.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysingh2025best

Related papers

• BEST-STD: Bidirectional Mamba-enhanced Speech Tokenization For Spoken Term Detection (2024)2.26
• A Nonparametric Bayesian Approach For Spoken Term Detection By Example Query (2016)0.00
• Query-by-example Spoken Term Detection Using Attention-based Multi-hop Networks (2017)9.23
• Cross-lingual And Multilingual Spoken Term Detection For Low-resource Indian Languages (2020)0.00
• Cross-lingual Query-by-example Spoken Term Detection: A Transformer-based Approach (2024)0.00
• Spoken Term Detection And Relevance Score Estimation Using Dot-product Of Pronunciation Embeddings (2022)5.84
• DASB - Discrete Audio And Speech Benchmark (2024)0.00
• Stabletoken: A Noise-robust Semantic Speech Tokenizer For Resilient Speechllms (2025)2.98