2019/10/21 by Shengye Wang, Wang, Shengye, Li Wan +6 · 10 citations
Computer Science · Engineering · Mathematics · #Audio and Speech Processing (eess.AS) #Computer science #FOS: Computer and information sciences #FOS: Electrical engineering #Identification (biology) #Linguistics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Natural language processing #Philosophy #Programming language #SIGNAL (programming language) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.LG #eess.AS #electronic engineering #information engineering #stat.ML
paper · pdf · doi:10.48550/arxiv.1910.09687
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/10/21 · arxiv created 2019/11/04 · arxiv updated 2019/11/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Google's multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This paper presents our experience with different signal combination methods to improve overall language identification accuracy. We compare the performance of a lattice-based ensemble model and a deep neural network model to combine signals from recognizers with that of a baseline that only uses low-level acoustic signals. Experimental results show that the deep neural network model outperforms the lattice-based ensemble model, and it reduced the error rate from 5.5% in the baseline to 4.3%, which is a 21.8% relative reduction.