arXiv AI September 17, 2026 By Aaron Yee, Fengjie Lu, Jiarui Hai, Chenang Jiang, Helin Wang, Siwei Tu, Weitao You, Lingyun Sun

VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval

Read the original on arXiv AI →

VoiceTrace introduces a new benchmark, VoiceTrace-Bench, for hybrid speech retrieval that combines a textual query specifying "what" to retrieve with a reference speech specifying "who" to retrieve. The authors propose a two‑stage framework: VoiceTrace‑Emb, which learns unified audio‑text embeddings for efficient large‑scale retrieval, and VoiceTrace‑Reranker, which fine‑grains relevance by jointly examining query‑candidate pairs. Experiments show VoiceTrace outperforms existing methods on both traditional semantic speech retrieval benchmarks and the new hybrid setting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 1

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

arXiv:2606. 30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space.

By Fengjie Lu, Chenang Jiang, Jiarui Hai, Helin Wang, Aaron Yee

llms rag nlp multimodal benchmarks

arXiv AI

Jul 15

SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise

arXiv:2602. 12783v3 Announce Type: replace-cross Abstract: Spoken query retrieval is an important interaction mode in modern information retrieval.

By Yuejie Li, Ke Yang, Yueying Hua, Berlin Chen, Jianhao Nie, Yueping He, Caixin Kang

benchmarks

arXiv AI

Jun 24

Event-Grounded Question Answering over Long Audio via Structured Retrieval

arXiv:2602. 14612v4 Announce Type: replace-cross Abstract: Answering natural-language questions over multi-hour audio requires both event recognition and temporal grounding.

By Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada, Yinyi Guo, Erik Visser

llms rag nlp benchmarks data-engineering

arXiv AI

Sep 23

Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval

arXiv:2609.23307v1 Announce Type: cross Abstract: This paper presents a comparative evaluation of dense embedding models for semantic candidate-job matching in high-volume staffing workflows. Incomin...

By Sai Yashwant, Siddhartha Jain, Anurag Dubey, Samaroha Chatterjee, Gantala Thulsiram

llms rag fine-tuning benchmarks

arXiv AI

Aug 28

A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers

The paper introduces STeReO, a reranker that orchestrates speech and text retrievers to aggregate evidence from heterogeneous databases. It addresses the scarcity of training data by curating a dataset of queries, mixed-modality evidence, and relevance rankings, then trains and evaluates the reranker in both single- and mixed-modality settings. Results show that STeReO effectively selects the most relevant evidence, leading to significant improvements in downstream question‑answering performance.

By Inho Kim, Sumyeong Ahn

llms rag multimodal safety

arXiv Computation and Language

Sep 3

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

SonicCaps is a large-scale audio captioning dataset featuring approximately 15 million captions paired with 700,000 audio clips, created using the Qwen3-Omni multimodal language model. The dataset emphasizes diversity by generating around 24 captions per clip through structured prompt engineering and few-shot generation, covering main descriptions, rephrased variants, and semantic tags. Human evaluations rate SonicCaps higher than existing datasets, and training CLAP models on it improves audio retrieval and zero-shot classification across public and commercial benchmarks.

By Zineb Lahrichi, Marc Ferras, Ga\"el Richard, Geoffroy Peeters

llms multimodal benchmarks

One email a morning, machine-written

Related stories

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise

Event-Grounded Question Answering over Long Audio via Structured Retrieval

Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval

A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval