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

arXiv: https://arxiv.org/abs/2609.18521 · HTML: https://mlsanity.com/paper/2609.18521/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 40 of its 47 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup](https://mlsanity.com/paper/2101.06983/) (2021)
- [A Theoretical Analysis of NDCG Type Ranking Measures](https://mlsanity.com/paper/1304.6480/) (2013)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [Spot the conversation: speaker diarisation in the wild](https://mlsanity.com/paper/2007.01216/) (2020)
- [Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension](https://mlsanity.com/paper/1804.00320/) (2018)
- [Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs](https://mlsanity.com/paper/2504.17432/) (2025)
- [A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models](https://mlsanity.com/paper/2310.09497/) (2023)
- [Scaling up masked audio encoder learning for general audio classification](https://mlsanity.com/paper/2406.06992/) (2024)
- [UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning](https://mlsanity.com/paper/2510.13515/) (2025)

## Abstract (arXiv)

Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing benchmarks and models have advanced semantic search over spoken content, but largely focus on what is said while overlooking who says it. In many real-world scenarios, however, users need to retrieve speech based jointly on semantic content and a target speaker, where the speaker may be specified naturally through a reference speech utterance rather than a predefined identity. To address this gap, we introduce VoiceTrace-Bench, a benchmark for hybrid speech retrieval in which each query combines text specifying what to retrieve with reference speech specifying who to retrieve. This setting requires models to integrate complementary semantic and speaker information directly from heterogeneous query inputs. Motivated by the joint audio-text modeling capabilities of audio-language models (ALMs), we develop VoiceTrace, a two-stage retrieval framework consisting of VoiceTrace-Emb, an embedding model that learns unified representations for efficient large-scale retrieval, and VoiceTrace-Reranker, a reranking model that jointly examines each query--candidate pair for fine-grained relevance estimation. Experiments show that VoiceTrace achieves state-of-the-art performance on established semantic speech retrieval benchmarks, while substantially outperforming cascade-based approaches on VoiceTrace-Bench, demonstrating its effectiveness for both conventional semantic retrieval and the new hybrid retrieval setting.