A Parametric Approach for Efficient Speech Storage, Flexible Synthesis and Voice Conversion

During the past decades, many areas of speech processing have benefited from the vast increases in the available memory sizes and processing power. For example, speech recognizers can be trained with enormous speech databases and high-quality speech synthesizers can generate new speech sentences by concatenating speech units retrieved from a large inventory of speech data. However, even in today's world of ever-increasing memory sizes and computational resources, there are still lots of embedded application scenarios for speech processing techniques where the memory capacities and the processor speeds are very limited. Thus, there is still a clear demand for solutions that can operate with limited resources, e.g., on low-end mobile devices. This thesis introduces a new segmental parametric speech codec referred to as the VLBR codec. The novel proprietary sinusoidal speech codec designed for efficient speech storage is capable of achieving relatively good speech quality at compression ratios beyond the ones offered by the standardized speech coding solutions, i.e., at bitrates of approximately 1 kbps and below. The efficiency of the proposed coding approach is based on model simplifications, mode-based segmental processing, and the method of adaptive downsampling and quantization. The coding efficiency is also further improved using a novel flexible multi-mode matrix quantizer structure and enhanced dynamic codebook reordering. The compression is also facilitated using a new perceptual irrelevancy removal method. The VLBR codec is also applied to text-to-speech synthesis. In particular, the codec is utilized for the compression of unit selection databases and for the parametric concatenation of speech units. It is also shown that the efficiency of the database compression can be further enhanced using speaker-specific retraining of the codec. Moreover, the computational load is significantly decreased using a new compression-motivated scheme for very fast and memory-efficient calculation of concatenation costs, based on techniques and implementations used in the VLBR codec. Finally, the VLBR codec and the related speech synthesis techniques are complemented with voice conversion methods that allow modifying the perceived speaker identity which in turn enables, e.g., cost-efficient creation of new text-to-speech voices. The VLBR-based voice conversion system combines compression with the popular Gaussian mixture model based conversion approach. Furthermore, a novel method is proposed for converting the prosodic aspects of speech. The performance of the VLBR-based voice conversion system is also enhanced using a new approach for mode selection and through explicit control of the degree of voicing. The solutions proposed in the thesis together form a complete system that can be utilized in different ways and configurations. The VLBR codec itself can be utilized, e.g., for efficient compression of audio books, and the speech synthesis related methods can be used for reducing the footprint and the computational load of concatenative text-to-speech synthesizers to levels required in some embedded applications. The VLBR-based voice conversion techniques can be used to complement the codec both in storage applications and in connection with speech synthesis. It is also possible to only utilize the voice conversion functionality, e.g., in games or other entertainment applications.

• speech