Enhancement of electrolarynx speech based on auditory masking

A preliminary study on improving the recognition of esophageal speech using a hybrid system based on statistical voice conversion

In this paper, we propose a hybrid system based on a modified statistical GMM voice conversion algorithm for improving the recognition of esophageal speech. This hybrid system aims to compensate for the distorted information present in the esophageal acoustic features by using a voice conversion method. The esophageal speech is converted into a “target” laryngeal speech using an iterative statistical estimation of a transformation function. We did not apply a speech synthesizer for reconstructing the converted speech signal, given that the converted Mel cepstral vectors are used directly as input of our speech recognition system. Furthermore the feature vectors are linearly transformed by the HLDA (heteroscedastic linear discriminant analysis) method to reduce their size in a smaller space having good discriminative properties. The experimental results demonstrate that our proposed system provides an improvement of the phone recognition accuracy with an absolute increase of 3.40 % when compared with the phone recognition accuracy obtained with neither HLDA nor voice conversion.

Reconstruction of normal sounding speech for laryngectomy patients through a modified CELP codec

Whispered speech can be useful for quiet and private communication, and is the primary means of unaided spoken communication for many people experiencing voice-box deficiencies. Patients who have undergone partial or full laryngectomy are typically unable to speak anything more than hoarse whispers, without the aid of prostheses or specialized speaking techniques. Each of the current prostheses and rehabilitative methods for post-laryngectomized patients (primarily oesophageal speech, tracheo-esophageal puncture, and electrolarynx) have particular disadvantages, prompting new work on nonsurgical, noninvasive alternative solutions. One such solution, described in this paper, combines whisper signal analysis with direct formant insertion and speech modification located outside the vocal tract. This approach allows laryngectomy patients to regain their ability to speak with a more natural voice than alternative methods, by whispering into an external prosthesis, which then, recreates and outputs natural-sounding speech. It relies on the observation that while the pitch-generation mechanism of laryngectomy patients is damaged or unusable, the remaining components of the speech production apparatus may be largely unaffected. This paper presents analysis and reconstruction methods designed for the prosthesis, and demonstrates their ability to obtain natural-sounding speech from the whisper-speech signal using an external analysis-by-synthesis processing framework.

Electrolarynx in voice rehabilitation

OBJECTIVE

Patients of laryngeal cancer who have undergone the surgical removal of the entire larynx suffer the loss of phonation. Electrolarynx (EL) speech is the most commonly adopted alaryngeal phonation. However, EL speech is notorious of the sound quality being monotonic and robotic with the lack of pitch control and the presence of the radiated noise. This paper provides a review of modalities in EL speech as well as introducing the technologies to control the pitch and reduce the noise of the device.

METHODS

Improvements of EL speech quality have been divided into two parts: improving the sound quality of EL device by applying different enhancement algorithms to reduce the radiated and the additive noise, and implementing pitch-control function to the EL with advanced technology.

RESULTS

Adaptive filtering and the subtractive-type algorithms have shown to be able to reduce the noise level associated with EL speech. And more mature technologies are showing promise to the making of a hand-free EL system producing more accurate and synchronized pitch and voice onset control.

CONCLUSION

The advent of micro-technology and human-machine integration promisingly improves EL speech quality and more efficient algorithms enhance EL sound quality. Such improvements apparently improve the intelligibility of EL speech, and thus better quality of life of the EL speakers.

Application of spectral subtraction method on enhancement of electrolarynx speech

Although electrolarynx (EL) serves as an important method of phonation for the laryngectomees, the resulting speech is of poor intelligibility due to the presence of a steady background noise caused by the instrument, even worse in the case of additive noise. This paper investigates the problem of EL speech enhancement by taking into account the frequency-domain masking properties of the human auditory system. One approach is incorporating an auditory masking threshold (AMT) for parametric adaptation in a subtractive-type enhancement process. The other is the supplementary AMT (SAMT) algorithm, which applies a cross-correlation spectral subtraction (CCSS) approach as a post-processing scheme to enhancing EL speech dealt with the AMT method. The performance of these two algorithms was evaluated as compared to the power spectral subtraction (PSS) algorithm. The best performance of EL speech enhancement was associated with the SAMT algorithm, followed by the AMT algorithm and the PSS algorithm. Acoustic and perceptual analyses indicated that the AMT and SAMT algorithms achieved the better performances of noise reduction and the enhanced EL speech was more pleasant to human listeners as compared to the PSS algorithm.