Maria Koutsogiannaki

Approaching speech intelligibility enhancement with inspiration from Lombard and Clear speaking styles

Lombard and Clear speech represent two acoustically and perceptually distinct speaking styles that humans employ to increase intelligibility. For Lombard speech, increased spectral energy in a band spanning the range of formants is consistent, effectively augmenting loudness, while vowel space expansion is exhibited in Clear speech, indicating greater articulation. On the other hand, analyses in the first part of this work illustrate that Clear speech does not exhibit significant spectral energy boosting, nor does the Lombard effect invoke an expansion of vowel space. Accordingly, though these two acoustic phenomena are largely attributed with the respective intelligibility gains of the styles, present analyses would suggest that they are mutually exclusive in human speech production. However, these phenomena can be used to inspire signal processing algorithms that seek to exploit and ultimately compound their respective intelligibility gains, as is explored in the second part of this work. While Lombard-inspired spectral shaping has been shown to successfully increase intelligibility, Clear speech-inspired modifications to expand vowel space are rarely explored. With this in mind, the latter part of this work focuses mainly on a novel frequency warping technique that is shown to achieve vowel space expansion. The frequency warping is then incorporated into an established Lombard-inspired Spectral Shaping method that pairs with dynamic range compression to maximize speech audibility (SSDRC). Finally, objective and subjective evaluations are presented in order to assess and compare the intelligibility gains of the different styles and their inspired modifications.

Modulation Enhancement of Temporal Envelopes for Increasing Speech Intelligibility in Noise.

In this paper, speech intelligibility is enhanced by manipulating the modulation spectrum of the signal. First, the signal is decomposed into Amplitude Modulation (AM) and Frequency Modulation (FM) components using a high resolution adaptive quasi-harmonic model of speech. Then, the AM part of midrange frequencies of speech spectrum is modified by applying a transforming function which follows the characteristics of the clear style of speaking. This results in increasing the modulation depth of the temporal envelopes of casual speech as in clear speech. The modified AM components of speech are then combined with the original FM parts to synthesize the final processed signal. Subjective listening tests evaluating the intelligibility of speech in noise showed that the suggested approach increases the intelligibility of speech by 40% on average, while it is comparable with recently suggested state-of-the-art algorithms of intelligibility boosters.

Simple and artefact-free spectral modifications for enhancing the intelligibility of casual speech

In this paper, the problem of modifying casual speech to reach the intelligibility level of clear speech is addressed. Unlike other studies, in this work modifications on casual speech both consider intelligibility and speech quality. To achieve this, the authors focus on human-like modifications inspired by clear speech. An acoustic analysis performed on clear and casual speech reveals energy differences on specific frequency bands between the two speaking styles. Then, a simple method is used to boost these frequency regions on casual speech. The proposed method, called mix-filtering, uses a multi-band filtering scheme to isolate the information of these frequency bands and then, add this information to the original signal. Our method is compared in terms of intelligibility and quality with unmodified casual speech and with a highly intelligible spectral modification technique, namely the Spectral Shaping and Dynamic Range Compression (SSDRC). Two different objective measures that are highly correlated with subjective intelligibility scores are used for estimating the intelligibility, whereas for evaluating the quality, preference listening tests are performed. Results show that the mix-filtering technique increases the intelligibility of casual speech while maintains its quality. On the other hand, while SSDRC outperforms on intelligibility, it degrades significantly the quality of casual speech.