Developed method of real-time non-uniform speech stretching is presented.The proposed solution is based on the well-known SOLA algorithm(Synchronous Overlap and Add). Non-uniform time-scale modification isachieved by the adjustment of time scaling factor values in accordance with thesignal content. Dependently on the speech unit (vowels/consonants), instantaneousrate of speech (ROS), and speech signal presence, values of the scalingfactor are selected. This provides as low as possible difference in the durationof the input and output signal and high naturalness and quality of the modifiedspeech. In the experimental part of the paper accuracy of the proposed ROS estimatoris examined. Quality of the speech stretched using the proposed methodis assessed in the subjective tests.
Authors
Additional information
- Category
- Publikacja w czasopiśmie
- Type
- artykuły w czasopismach recenzowanych i innych wydawnictwach ciągłych
- Language
- angielski
- Publication year
- 2012
