Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion

TL;DR

This paper enhances speech intelligibility in noisy environments by converting non-professional voices to sound like professional announcers, leveraging voice conversion techniques to improve clarity especially at low SNR levels.

Contribution

It introduces a novel voice conversion approach to mimic professional announcer voices, improving speech clarity in noisy settings, and demonstrates the effectiveness through objective and subjective evaluations.

Findings

Converted voices show higher intelligibility than original voices in noise.

Professional and non-professional voices form distinct clusters in speaker embedding space.

Voice conversion improves speech clarity at low SNR levels.

Abstract

In most of practical scenarios, the announcement system must deliver speech messages in a noisy environment, in which the background noise cannot be cancelled out. The local noise reduces speech intelligibility and increases listening effort of the listener, hence hamper the effectiveness of announcement system. There has been reported that voices of professional announcers are clearer and more comprehensive than that of non-expert speakers in noisy environment. This finding suggests that the speech intelligibility might be related to the speaking style of professional announcer, which can be adapted using voice conversion method. Motivated by this idea, this paper proposes a speech intelligibility enhancement in noisy environment by applying voice conversion method on non-professional voice. We discovered that the professional announcers and non-professional speakers are clusterized into different clusters on the speaker embedding plane. This implies that the speech intelligibility can be controlled as an independent feature of speaker individuality. To examine the advantage of converted voice in noisy environment, we experimented using test words masked in pink noise at different SNR levels. The results of objective and subjective evaluations confirm that the speech intelligibility of converted voice is higher than that of original voice in low SNR conditions.