Speech synthesis is an automatic encoding process carried out by machine through which symbols conveying linguistic information are converted into an acoustic waveform. In the past decade or so, a recent trend toward a non-parametric, corpus-based approach has focused on using real human speech as source material for producing novel natural-sounding speech. This work proposes a communication-theoretic formulation in which unit selection is a noisy channel through which an input sequence of symbols passes and an output sequence, possibly corrupted due to the coverage limits of the corpus, emerges. The penalty of approximation is quantified by substitution and concatenation costs which grade what unit contexts are interchangeable and where concatenations are not perceivable. These costs are semi-automatically derived from data and are found to agree with acoustic-phonetic knowledge. The implementation is based on a finite-state transducer (FST) representation that has been successfully used in speech and language processing applications including speech recognition. A proposed constraint kernel topology connects all units in the corpus with associated substitution and concatenation costs and enables an efficient Viterbi search that operates with low latency and scales to large corpora. An A* search can be applied in a second, rescoring pass to incorporate finer acoustic modelling. Extensions to this FST-based search include hierarchical and paralinguistic modelling. The search can also be used in an iterative feedback loop to record new utterances to enhance corpus coverage. This speech synthesis framework has been deployed across various domains and languages in many voices, a testament to its flexibility and rapid prototyping capability.
展开▼
