Abstract | ||
---|---|---|
This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio. Firstly, we thoroughly update the model architecture that was previously designed based on a long short-term memory (LSTM)-based attention encoder decoder by applying transformer architectures. Secondly, we propose a speaker deduplication mechanism to reduce speaker identification errors in highly overlapped regions. Experimental results on the LibriSpeechMix dataset shows that the transformer-based architecture is especially good at counting the speakers and that the proposed model reduces the speaker-attributed word error rate by 47% over the LSTM-based baseline. Furthermore, for the LibriCSS dataset, which consists of real recordings of overlapped speech, the proposed model achieves concatenated minimum-permutation word error rates of 11.9% and 16.3% with and without target speaker profiles, respectively, both of which are the state-of-the-art results for LibriCSS with the monaural setting. |
Year | DOI | Venue |
---|---|---|
2021 | 10.21437/Interspeech.2021-101 | Interspeech |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Naoyuki Kanda | 1 | 103 | 19.45 |
Guoli Ye | 2 | 8 | 3.16 |
Yashesh Gaur | 3 | 15 | 9.06 |
Xiaofei Wang | 4 | 5 | 4.14 |
Zhong Meng | 5 | 33 | 14.95 |
Zhuo Chen | 6 | 153 | 24.33 |
Takuya Yoshioka | 7 | 585 | 49.20 |