Journal Article

Whisper-to-speech conversion using restricted Boltzmann machine arrays

Li, Jing-jie, McLoughlin, Ian V., Dai, Li-Rong, Ling, Zhen-hua

2014

Overview

Whispers are a natural vocal communication mechanism, in which vocal cords do not vibrate normally. Lack of glottal-induced pitch leads to low energy, and an inherent noise-like spectral distribution reduces intelligibility. Much research has been devoted to processing of whispers, including conversion of whispers to speech. Unfortunately, among several approaches, the best reconstructed speech to date still contains obviously artificial muffles and suffers from an unnatural prosody. To address these issues, the novel use of multiple restricted Boltzmann machines (RBMs) is reported as a statistical conversion model between whisper and speech spectral envelopes. Moreover, the accuracy of estimated pitch is improved using machine learning techniques for pitch estimation within only voiced (V) regions. Both objective and subjective evaluations show that this new method improves the quality of whisper-reconstructed speech compared with the state-of-the-art approaches.

• Publisher: The Institution of Engineering and Technology,John Wiley & Sons, Inc
• Subject: Acoustical engineering / Arrays / artificial muffle / Boltzmann machines / Conversion / Gaussian mixture model / glottal‐induced pitch lead / human‐to‐human vocal communication mechanism / inherent noise‐like spectral distribution / Intelligibility / learning (artificial intelligence) / Linguistics / Machine learning / machine learning technique / pitch accuracy / pitch estimation / RBM arrays / restricted Boltzmann machine array / Spectra / Speech / speech intelligibility / speech processing / speech reconstruction / speech spectral envelope / State of the art / statistical analysis / statistical conversion model / unnatural prosody / vocal cord / Vocal cords / voiced region / whisper processing / whisper‐to‐speech conversion