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

arXiv:2609.18521v1 Announce Type: cross Abstract: 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 extbf{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 extbf{VoiceTrace}, a two-stage retrieval framework consisting of extbf{VoiceTrace-Emb}, an embedding model that learns unified representations for efficient large-scale retrieval, and extbf{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.

Source: arXiv cs.AI | 2026-09-17

Related