A Hybrid Text-to-Speech System That Combines Concatenative and Statistical Synthesis Units

• Published in: IEEE transactions on audio, speech, and language processing Vol. 19; no. 5; pp. 1278 - 1288
• Main Authors: Tiomkin, S, Malah, D, Shechtman, S, Kons, Z
• Format: Journal Article
• Language: English
• Published: Piscataway, NJ IEEE 01.07.2011; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Concatenative text-to-speech (CTTS); Discontinuity; dynamic path; Dynamics; Exact sciences and technology; Footprints; Heuristic algorithms; Hidden Markov models; Hybrid power systems; hybrid TTS; Information, signal and communications theory; Natural languages; Segments; Signal processing; Speech; Speech processing; Speech recognition; statistical TTS; Synthesis; Telecommunications and information theory; TTS synthesis; statistical TTS; Segmentation; Sound quality; dynamic path; hybrid TTS; Speech synthesis; Algorithm; Hybrid system; Concatenative text-to-speech (CTTS); Linguistic analysis; Concatenation; TTS synthesis; Database; System synthesis
• ISSN: 1558-7916; 1558-7924
• DOI: 10.1109/TASL.2010.2089679

Concatenative synthesis and statistical synthesis are the two main approaches to text-to-speech (TTS) synthesis. Concatenative TTS (CTTS) stores natural speech features segments, selected from a recorded speech database. Consequently, CTTS systems enable speech synthesis with natural quality. However, as the footprint of the stored data is reduced, desired segments are not always available in the stored data, and audible discontinuities may result. On the other hand, statistical TTS (STTS) systems, in spite of having a smaller footprint than CTTS, synthesize speech that is free of such discontinuities. Yet, in general, STTS produces lower quality speech than CTTS, in terms of naturalness, as it is often sounding muffled. The muffling effect is due to over-smoothing of model-generated speech features. In order to gain from the advantages of each of the two approaches, we propose in this work to combine CTTS and STTS into a hybrid TTS (HTTS) system. Each utterance representation in HTTS is constructed from natural segments and model generated segments in an interweaved fashion via a hybrid dynamic path algorithm. Reported listening tests demonstrate the validity of the proposed approach.