Attention based end to end Speech Recognition for Voice Search in Hindi and English

Abstract

We describe here our work with automatic speech recognition (ASR) in the context of voice search functionality on the Flipkart e-Commerce platform. Starting with the deep learning architecture of Listen-Attend-Spell (LAS), we build upon and expand the model design and attention mechanisms to incorporate innovative approaches including multi-objective training, multi-pass training, and external rescoring using language models and phoneme based losses. We report a relative WER improvement of 15.7% on top of state-of-the-art LAS models using these modifications. Overall, we report an improvement of 36.9% over the phoneme-CTC system. The paper also provides an overview of different components that can be tuned in a LAS-based system.

Accepted at Forum for Information Retrieval Evaluation (FIRE) 2021

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• An Overview of Multi-Task Learning in Deep Neural Networks
• Attention-Based Models for Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• Conformer: Convolution-augmented Transformer for Speech Recognition
• Transfer Learning Approaches for Streaming End-to-End Speech Recognition System

Cited by in corpus (3)

• A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data
• Code-Mixed Text to Speech Synthesis under Low-Resource Constraints
• On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode