Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers

Autor:	Kanda, Naoyuki, Gaur, Yashesh, Wang, Xiaofei, Meng, Zhong, Chen, Zhuo, Zhou, Tianyan, Yoshioka, Takuya
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Computation and Language Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training (SOT) with attention-based encoder-decoder, a recently proposed method for recognizing overlapped speech comprising an arbitrary number of speakers. We extend SOT by introducing a speaker inventory as an auxiliary input to produce speaker labels as well as multi-speaker transcriptions. All model parameters are optimized by speaker-attributed maximum mutual information criterion, which represents a joint probability for overlapped speech recognition and speaker identification. Experiments on LibriSpeech corpus show that our proposed method achieves significantly better speaker-attributed word error rate than the baseline that separately performs overlapped speech recognition and speaker identification. Comment: Accepted to INTERSPEECH 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2006.10930 Zobrazit plný text záznamu View this record from Arxiv