collaborators

5 papers

eess.AS2024

Zero-shot Cross-lingual Voice Transfer for TTS

Fadi Biadsy, Youzheng Chen, Isaac Elias +4

In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to transfer an individual's vo…

cs.SD2024

Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting

Hyun Jin Park, Dhruuv Agarwal, Neng Chen +10

The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speec…

cs.SD2024

Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model

Hyun Jin Park, Dhruuv Agarwal, Neng Chen +10

This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amou…

eess.AS2024

Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data

Takaaki Saeki, Gary Wang, Nobuyuki Morioka +8

Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a framework for scaling a…

eess.AS2024

ASTRA: Aligning Speech and Text Representations for Asr without Sampling

Neeraj Gaur, Rohan Agrawal, Gary Wang +3

This paper introduces ASTRA, a novel method for improving Automatic Speech Recognition (ASR) through text injection.Unlike prevailing techniques, ASTRA eliminates the need for samp…