Problem
Research questions and friction points this paper is trying to address.
speech source tracking
data association
direction-of-arrival (DOA)
speaker identity
Identity-Assisted Association of Unordered DOA Estimates for Neural Speech Source Tracking
🤖 AI Summary
This study addresses the data association ambiguity in unordered direction-of-arrival (DOA) estimation caused by speech intermittency, spatial proximity, and complex acoustic environments. To this end, we propose an identity-assisted multi-speaker tracking method that innovatively fuses long-term stable speaker embeddings with short-term continuous spatial cues. A unified neural tracker is designed to map multi-source observations into consistent identity trajectories by leveraging a temporal self-attention module to capture trajectory evolution and a source attention mechanism to disambiguate competing tracks. Experimental results demonstrate that the proposed approach effectively mitigates association confusion under multi-source competition, significantly enhancing the reliability of speech source tracking in complex scenarios.
📝 Abstract
Tracking speech sources remains a challenge due to ambiguous data association arising from intermittent speech, close spatial proximity, and complex acoustic conditions. To address these issues, we propose an identity-assisted association that maps unordered direction-of-arrival (DOA) estimates to speaker-consistent source trajectories for reliable speech source tracking. Specifically, speaker identity embeddings are directly integrated into the model input as a complementary cue to spatial features. This enables maintaining identity consistency by combining long-term time-invariant vocal identity characteristics with the short-term continuity of spatial cues. To effectively process these heterogeneous inputs while accommodating their distinct characteristics, we design a unified neural tracker. Within this model, time self-attention modules capture the temporal evolution of each source, while source self-attention modules distinguish between competing source tracks. Experimental results demonstrate the superiority of the proposed neural tracker in mitigating association confusion for speech source tracking.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Identity-assisted association
Direction-of-arrival (DOA) estimation
Neural speech source tracking
Speaker identity embeddings
Self-attention modules
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
