Paper ID | SPE-40.2 | ||
Paper Title | STREAMING END-TO-END SPEECH RECOGNITION WITH JOINTLY TRAINED NEURAL FEATURE ENHANCEMENT | ||
Authors | Chanwoo Kim, Abhinav Garg, Dhananjaya Gowda, Seongkyu Mun, Changwoo Han, Samsung Research, South Korea | ||
Session | SPE-40: Speech Recognition 14: Acoustic Modeling 2 | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 15:30 - 16:15 | ||
Presentation Time: | Thursday, 10 June, 15:30 - 16:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-RECO] Acoustic Modeling for Automatic Speech Recognition | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In this paper, we present a streaming end-to-end speech recognition model based on Monotonic Chunkwise Attention (MoCha) jointly trained with enhancement layers. Even though the MoCha attention enables streaming speech recognition with recognition accuracy comparable to a full attention-based approach, training this model is sensitive to various factors such as the difficulty of training examples, hyper-parameters, and so on. Because of these issues, speech recognition accuracy of a Mocha-based model for clean speech drops significantly when a multi-style training approach is applied. Inspired by Curriculum Learning [1], we introduce two training strategies: Gradual Application of Enhanced Features (GAEF) and Gradual Reduction of Enhanced Loss (GREL). With GAEF, the model is initially trained using clean features. Subsequently, the portion of outputs from the enhancement layers gradually increases. With GREL, the portion of the Mean Squared Error (MSE) loss for the enhanced output gradually reduces as training proceeds. In experimental results on the LibriSpeech corpus and noisy far-field test sets, the proposed model with GAEF-GREL training strategies shows significantly better results than the conventional multi-style training approach. |