Speech Activity Detection Based On Multilingual Speech Recognition System

Abstract

To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech Recognition (ASR) system to perform SAD. Sequence discriminative training of Acoustic Model (AM) using Lattice-Free Maximum Mutual Information (LF-MMI) loss function, effectively extracts the contextual information of the input acoustic frame. Multi-lingual AM training, causes the robustness to noise and language variabilities. The index of maximum output posterior is considered as a frame-level speech/non-speech decision function. Majority voting and logistic regression are applied to fuse the language-dependent decisions. The multi-lingual ASR is trained on 18 languages of BABEL datasets and the built SAD is evaluated on 3 different languages. On out-of-domain datasets, the proposed SAD model shows significantly better performance with respect to baseline models. On the Ester2 dataset, without using any in-

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysarfjoo2020speech

Related papers

• Temporarily-aware Context Modelling Using Generative Adversarial Networks For Speech Activity Detection (2020)7.50
• End-to-end Audiovisual Speech Activity Detection With Bimodal Recurrent Neural Models (2018)10.48
• Incorporating VAD Into ASR System By Multi-task Learning (2021)4.52
• Multilingual Sequence-to-sequence Speech Recognition: Architecture, Transfer Learning, And Language Modeling (2018)13.84
• Analysis Of Multilingual Sequence-to-sequence Speech Recognition Systems (2018)0.00
• Building Robust And Scalable Multilingual ASR For Indian Languages (2025)0.00
• Streaming Language Identification Using Combination Of Acoustic Representations And ASR Hypotheses (2020)0.00
• Adaptive Activation Network For Low Resource Multilingual Speech Recognition (2022)0.00