Text-to-speech Synthesis System Research Articles

Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis

Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality speech directly from text or simple linguistic features such as phonemes. Unlike traditional pipeline TTS, the neural sequence-to-sequence TTS does not require manually annotated and complicated linguistic features such as part-of-speech tags and syntactic structures for system training. However, it must be carefully designed and well optimized so that it can implicitly extract useful linguistic features from the input features.In this paper we investigate under what conditions the neural sequence-to-sequence TTS can work well in Japanese and English along with comparisons with deep neural network (DNN) based pipeline TTS systems. Unlike past comparative studies, the pipeline systems also use neural autoregressive (AR) probabilistic modeling and a neural vocoder in the same way as the sequence-to-sequence systems do for a fair and deep analysis in this paper. We investigated systems from three aspects: a) model architecture, b) model parameter size, and c) language. For the model architecture aspect, we adopt modified Tacotron systems that we previously proposed and their variants using an encoder from Tacotron or Tacotron2. For the model parameter size aspect, we investigate two model parameter sizes. For the language aspect, we conduct listening tests in both Japanese and English to see if our findings can be generalized across languages.Our experiments on Japanese demonstrated that the Tacotron TTS systems with increased parameter size and input of phonemes and accentual type labels outperformed the DNN-based pipeline systems using the complicated linguistic features and that its encoder could learn to compensate for a lack of rich linguistic features. Our experiments on English demonstrated that, when using a suitable encoder, the Tacotron TTS system with characters as input can disambiguate pronunciations and produce natural speech as good as those of the systems using phonemes. However, we also found that the encoder could not learn English stressed syllables from characters perfectly and hence resulted in flatter fundamental frequency. In summary, these experimental results suggest that a) a neural sequence-to-sequence TTS system should have a sufficient number of model parameters to produce high quality speech, b) it should also use a powerful encoder when it takes characters as inputs, and c) the encoder still has a room for improvement and needs to have an improved architecture to learn supra-segmental features more appropriately.

Development of Unit Selection Based Speech Synthesis System

This paper presents the design and implementation of restricted text to speech synthesis (TTS) system in Hindi. Restricted TTS system has ability to synthesize good quality of speech in specific domain. In this work, Phonemes are used as basic units for synthesis. Speech database is generated using Hidden Markov Model (HMM). The framework is indigenously implemented in laboratory on visual basic platform using C. Speech is collected from a male speaker is used as speech corpus. The TTS system comprises of various modules, a text analyzer, speech database with phonemes recorded, a unit selection module and a synthesizer. Speech database was created through an automated speech segmentation based on Hidden Markov Model (HMM). A subjective score shows an average of 3.698 mean opinion score as compared to 4.5 given to natural speech.

Speech Synthesis System for Marathi Accent using FESTVOX

Text To Speech synthesis (TTS) is the production of artificial speech by a machine for the given text as input. This field of study is known both as Speech Synthesis that is the synthetic (computer) generation of speech, and Text-To- Speech or TTS. It is the process of converting written text into speech. In the process of speech synthesis, mainly two processing components are used; they are NLP (natural language processing) and DSP (digital signal processing) modules. The speech synthesis has enormous applications such as reading for blind people, telecommunication services, language education, and aid to handicapped persons, talking books and toys, call center automation etc. The main aim of the project is to develop a TTS system producing a voice with Indian accent for the given input text. In this project, for the conversion of text to speech, we use Festival in Linux environment. Festival is a general pre-packaged tool for development of multi-language speech synthesis systems; and it will support most of the languages in the text to speech conversion. In this project, the speech generation process is done by using Festival frame work and speech tools. The voice model is generated by using festvox frame work, festival and speech tools. The required speech data for generating voice is recorded in noise less environment. The voice models can be generated by unit selection or clustergen modules present in festvox. It is observed from the generated voices that clustergen voices are better than unit selection voices.

Prosody modeling for syllable based text-to-speech synthesis using feedforward neural networks

Prosody plays an important role in improving the quality of text-to-speech synthesis (TTS) system. In this paper, features related to the linguistic and the production constraints are proposed for modeling the prosodic parameters such as duration, intonation and intensities of the syllables. The linguistic constraints are represented by positional, contextual and phonological features, and the production constraints are represented by articulatory features. Neural network models are explored to capture the implicit duration, F0 and intensity knowledge using above mentioned features. The prediction performance of the proposed neural network models is evaluated using objective measures such as average prediction error (μ), standard deviation (σ) and linear correlation coefficient (γX,Y). The prediction accuracy of the proposed neural network models is compared with other state-of-the-art prosody models used in TTS systems. The prediction accuracy of the proposed prosody models is also verified by conducting listening tests, after integrating the proposed prosody models to the baseline TTS system.

Development of syllable-based text to speech synthesis system in Bengali

This paper presents the design and development of unrestricted text to speech synthesis (TTS) system in Bengali language. Unrestricted TTS system is capable to synthesize good quality of speech in different domains. In this work, syllables are used as basic units for synthesis. Festival framework has been used for building the TTS system. Speech collected from a female artist is used as speech corpus. Initially five speakers' speech is collected and a prototype TTS is built from each of the five speakers. Best speaker among the five is selected through subjective and objective evaluation of natural and synthesized waveforms. Then development of unrestricted TTS is carried out by addressing the issues involved at each stage to produce good quality synthesizer. Evaluation is carried out in four stages by conducting objective and subjective listening tests on synthesized speech. At the first stage, TTS system is built with basic festival framework. In the following stages, additional features are incorporated into the system and quality of synthesis is evaluated. The subjective and objective measures indicate that the proposed features and methods have improved the quality of the synthesized speech from stage-2 to stage-4.

Time and space-efficient architecture for a corpus-based text-to-speech synthesis system

This paper proposes a time and space-efficient architecture for a text-to-speech synthesis system (TTS). The proposed architecture can be efficiently used in those applications with unlimited domain, requiring multilingual or polyglot functionality. The integration of a queuing mechanism, heterogeneous graphs and finite-state machines gives a powerful, reliable and easily maintainable architecture for the TTS system. Flexible and language-independent framework efficiently integrates all those algorithms used within the scope of the TTS system. Heterogeneous relation graphs are used for linguistic information representation and feature construction. Finite-state machines are used for time and space-efficient representation of language resources, for time and space-efficient lookup processes, and the separation of language-dependent resources from a language-independent TTS engine. Its queuing mechanism consists of several dequeue data structures and is responsible for the activation of all those TTS engine modules having to process the input text. In the proposed architecture, all modules use the same data structure for gathering linguistic information about input text. All input and output formats are compatible, the structure is modular and interchangeable, it is easily maintainable and object oriented. The proposed architecture was successfully used when implementing the Slovenian PLATTOS corpus-based TTS system, as presented in this paper.