To address the challenge of limited in-domain data, we use cross-bandwidth and cross-lingual transfer learning methods to leverage knowledge from other domains ...

This work investigates ways to improve DNN acoustic models for Bluetooth narrowband mobile applications when relatively small amounts of in-domain training ...

Aug 1, 2017 · Conclusions. We leverage knowledge from other speech recognition tasks to improve DNN acoustic models for narrowband Bluetooth applications.

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-bandwidth and Cross-lingual Initialization, INTERSPEECH 2017. Page 8. Large-scale Mixed-bandwidth ...

Sep 26, 2024 · Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization. INTERSPEECH 2017: 2148-2152; 2015.

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-bandwidth and Cross-lingual Initialization. X Zhuang, A Ghoshal, AV Rosti, M Paulik, D Liu.

Aug 24, 2017 · Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization Xiaodan Zhuang, Arnab Ghoshal, Antti ...

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization. INTERSPEECH 2017: 2148-2152. [+][–]. Coauthor network.

In this paper, we present our initial efforts for building a code-switching (CS) speech recognition system leveraging existing acoustic models (AMs) and ...

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization (conference). Zhuang, Xiaodan | Ghoshal, Arnab | Rosti ...