Towards Relevance And Sequence Modeling In Language Recognition

Abstract

The task of automatic language identification (LID) involving multiple dialects of the same language family in the presence of noise is a challenging problem. In these scenarios, the identity of the language/dialect may be reliably present only in parts of the temporal sequence of the speech signal. The conventional approaches to LID (and for speaker recognition) ignore the sequence information by extracting long-term statistical summary of the recording assuming an independence of the feature frames. In this paper, we propose a neural network framework utilizing short-sequence information in language recognition. In particular, a new model is proposed for incorporating relevance in language recognition, where parts of speech data are weighted more based on their relevance for the language recognition task. This relevance weighting is achieved using the bidirectional long short-term memory (BLSTM) network with attention modeling. We explore two approaches, the first approach uses segme

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keypadi2020towards

Related papers

• Streaming Language Identification Using Combination Of Acoustic Representations And ASR Hypotheses (2020)0.00
• Multi-language Identification Using Convolutional Recurrent Neural Network (2016)13.88
• Multi-dialect Speech Recognition With A Single Sequence-to-sequence Model (2017)13.79
• Utterance-level End-to-end Language Identification Using Attention-based CNN-BLSTM (2019)11.67
• On Using 2D Sequence-to-sequence Models For Speech Recognition (2019)0.00
• Multilingual Sequence-to-sequence Speech Recognition: Architecture, Transfer Learning, And Language Modeling (2018)13.84
• Joint Language Identification Of Code-switching Speech Using Attention Based E2E Network (2019)5.24
• Segment Relevance Estimation For Audio Analysis And Weakly-labelled Classification (2019)0.00