# Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition

## TL;DR

This paper explores large-scale mixed-bandwidth deep neural network acoustic modeling for automatic speech recognition, integrating wideband and narrowband data to improve system deployment and performance.

## Contribution

It introduces and evaluates various mixed-bandwidth strategies, including downsampling, upsampling, and bandwidth extension, for large-scale DNN acoustic modeling.

## Key findings

- Mixed-bandwidth strategies improve ASR accuracy across diverse datasets.
- Distributed training enables handling large-scale data efficiently.
- Evaluation on multiple datasets demonstrates robustness of proposed methods.

## Abstract

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values for ASR system deployment. In this paper, we extensively investigate large-scale MB deep neural network acoustic modeling for ASR using 1,150 hours of WB data and 2,300 hours of NB data. We study various MB strategies including downsampling, upsampling and bandwidth extension for MB acoustic modeling and evaluate their performance on 8 diverse WB and NB test sets from various application domains. To deal with the large amounts of training data, distributed training is carried out on multiple GPUs using synchronous data parallelism.