Language Identification With Deep Bottleneck Features

Abstract

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features used for LSTM learning are generated by a transfer learning method. Bottle-neck features of a deep neural network (DNN) which are trained for mandarin acoustic-phonetic classification are used for LSTM training. In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance. By splicing the normal, speech rate reduced and increased utterances, we can extend length of test utterances so as to improved improved the performance of the SLD system. The experimental results on AP17-OLR database shows that the proposed methods can improve the performance of SLD, especially on short utterance with 1s and 3s durations.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyma2018language

Related papers

• Time-contrastive Learning Based Deep Bottleneck Features For Text-dependent Speaker Verification (2019)9.92
• Phonetic Temporal Neural Model For Language Identification (2017)12.40
• Dnn-based Cross-lingual Voice Conversion Using Bottleneck Features (2019)3.58
• Utterance-level End-to-end Language Identification Using Attention-based CNN-BLSTM (2019)11.67
• Time-contrastive Learning Based DNN Bottleneck Features For Text-dependent Speaker Verification (2017)9.92
• An Attention Long Short-term Memory Based System For Automatic Classification Of Speech Intelligibility (2024)12.33
• LSTM-TDNN With Convolutional Front-end For Dialect Identification In The 2019 Multi-genre Broadcast Challenge (2019)0.00
• Deep LSTM For Large Vocabulary Continuous Speech Recognition (2017)14.58