Target-Speaker Voice Activity Detection Via Sequence-to-Sequence Prediction
Ming Cheng, Weiqing Wang, Yucong Zhang, Xiaoyi Qin, Ming Li
Abstract
Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments. This paper presents a novel Sequence-to-Sequence Target-Speaker Voice Activity Detection (Seq2Seq-TSVAD) method that can efficiently address the joint modeling of large-scale speakers and predict high-resolution voice activities. Experimental results show that larger speaker capacity and higher output resolution can significantly reduce the diarization error rate (DER), which achieves the new state-of-the-art performance of 4.55% on the VoxConverse test set and 10.77% on Track 1 of the DIHARD-III evaluation set under the widely-used evaluation metrics.
Topics & Concepts
Computer scienceSpeaker diarisationSpeech recognitionSequence (biology)Set (abstract data type)Speaker recognitionVoice activity detectionTest setWord error rateJoint (building)Artificial intelligencePattern recognition (psychology)Speech processingEngineeringArchitectural engineeringGeneticsProgramming languageBiologySpeech and Audio ProcessingSpeech Recognition and SynthesisMusic and Audio Processing